© 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. 62667
    Prev
    Next
    INDEX
    Explanations

    previous season

    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
    Ο
    -0.86
    bury
    -0.84
    ੋਂ
    -0.83
    Son
    -0.82
    JM
    -0.80
    Dur
    -0.79
    '">
    -0.78
     pokoje
    -0.78
    如今
    -0.77
    asin
    -0.77
    POSITIVE LOGITS
    quierda
    0.81
     يعني
    0.77
     jusque
    0.76
    ברית
    0.75
    hova
    0.74
     oldValue
    0.73
    ネート
    0.72
    ǫ
    0.71
     groupName
    0.71
    Cinta
    0.71
    Activations Density 0.003%

    No Known Activations