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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117217
    Prev
    Next
    INDEX
    Explanations

    javascript jquery ajax calls

    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
    家は
    -0.91
    satunya
    -0.86
    ších
    -0.86
    меня
    -0.83
     gainera
    -0.80
     Szer
    -0.79
    另一方面
    -0.79
     Octa
    -0.78
    需要的
    -0.77
     to
    -0.77
    POSITIVE LOGITS
    each
    1.02
    ajax
    0.93
    +"&
    0.89
    litre
    0.87
    NBT
    0.86
     パリ
    0.84
    関連リンク
    0.84
    removeClass
    0.83
    .’”
    0.83
     solidif
    0.81
    Activations Density 0.008%

    No Known Activations