© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47403
    Prev
    Next
    INDEX
    Explanations

    Role of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     может
    -0.91
    springframework
    -0.87
    ᥕ
    -0.86
    fieldname
    -0.79
    Ĵ
    -0.79
    Tran
    -0.77
    Вы
    -0.77
    しかも
    -0.77
    Parm
    -0.75
    pgsql
    -0.75
    POSITIVE LOGITS
    othes
    0.83
    internal
    0.79
     إف
    0.79
     artisanal
    0.79
    łby
    0.77
    inf
    0.73
     internal
    0.73
    buje
    0.72
     affect
    0.71
     Detox
    0.71
    Activations Density 0.024%

    No Known Activations