© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 992
    Prev
    Next
    INDEX
    Explanations

    elders and lists

    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
    サーバー
    0.35
    nostic
    0.33
    $}}
    0.33
     dieser
    0.32
    內的
    0.31
    ਿਤ
    0.31
    ந்திரன்
    0.30
     ব্যবহৃত
    0.29
    கன்
    0.29
    攻撃
    0.29
    POSITIVE LOGITS
     এবং
    0.66
     và
    0.63
     and
    0.62
    และ
    0.62
     आणि
    0.61
     و
    0.60
     и
    0.59
     અને
    0.59
     और
    0.56
     และ
    0.54
    Activations Density 2.916%

    No Known Activations