© 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. 22-GEMMASCOPE-RES-131K
    7. 129351
    Prev
    Next
    INDEX
    Explanations

    code blocks and control flow

    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_22/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
     سپس
    -0.98
     then
    -0.92
    sodik
    -0.91
    옴
    -0.91
     ume
    -0.91
    おそ
    -0.90
    5
    -0.88
    iamo
    -0.85
     チェーン
    -0.84
     uniti
    -0.84
    POSITIVE LOGITS
     meleg
    0.98
    cloudf
    0.96
     mert
    0.94
    |^{
    0.93
     tém
    0.92
    лії
    0.92
    cians
    0.92
    gonic
    0.90
    kumpulan
    0.90
    клон
    0.89
    Activations Density 0.002%

    No Known Activations