© 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. 10-GEMMASCOPE-RES-131K
    7. 58318
    Prev
    Next
    INDEX
    Explanations

    often and frequently

    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_10/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
    {
    -1.83
     a
    -1.72
    .!
    -1.71
    嶮
    -1.69
     to
    -1.67
    would
    -1.56
     further
    -1.51
    迓
    -1.47
    [
    -1.47
     senza
    -1.45
    POSITIVE LOGITS
     berusia
    1.75
     autres
    1.73
     بسیار
    1.71
     lainnya
    1.67
     memutuskan
    1.63
    ギュア
    1.60
    Другие
    1.55
     ideen
    1.55
    ！”
    1.52
    Работа
    1.52
    Activations Density 0.037%

    No Known Activations