Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 27864
    Prev
    Next
    INDEX
    Explanations

    proper nouns and named entities across multiple languages and domains.

    oai_token-act-pair · claude-4-5-haikuTriggered by @gersonkroiz

    technical and procedural descriptions related to network communication.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    Slavic patronymics like 'ovich'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ı
    0.13
    ama
    0.13
    ara
    0.12
    us
    0.12
    á
    0.11
    í
    0.11
    es
    0.11
    ed
    0.11
    ८
    0.11
    if
    0.11
    POSITIVE LOGITS
     transformasi
    0.11
     crows
    0.11
     extinguish
    0.11
     realms
    0.11
     swarm
    0.11
    Webhook
    0.10
     annih
    0.10
     gyms
    0.10
    InCM
    0.10
     zones
    0.10
    Activations Density 0.000%

    No Known Activations