© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166511
    Prev
    Next
    INDEX
    Explanations

    ban laws

    np_acts-logits-general · gemini-2.5-flash-lite

    imagine, business driver, server, vaccine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بأن
    0.46
     poj
    0.45
    填写
    0.43
     Bounce
    0.43
     单
    0.43
     اللجنة
    0.43
    SelectSingle
    0.43
     اتفاق
    0.43
     ज्या
    0.42
    志森
    0.42
    POSITIVE LOGITS
    achts
    0.47
    acher
    0.44
    サッカー
    0.44
    ൨
    0.43
    nc
    0.43
    ಾನೆ
    0.43
    ourses
    0.42
    tabla
    0.42
    スタジオ
    0.42
    довж
    0.42
    Activations Density 0.000%

    No Known Activations