© 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. 22505
    Prev
    Next
    INDEX
    Explanations

    exexception and examples

    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
    ↵
    -1.81
     a
    -1.73
     largely
    -1.65
    愎
    -1.63
    事も
    -1.60
     That
    -1.59
     codice
    -1.59
    CHREIB
    -1.55
     ativa
    -1.54
     orchestrated
    -1.52
    POSITIVE LOGITS
    _
    2.03
    嚳
    1.70
    ୈ
    1.70
    thenburg
    1.65
    텃
    1.63
     الدولي
    1.63
    錚
    1.62
    ጁ
    1.60
    廚
    1.59
    飒
    1.59
    Activations Density 0.003%

    No Known Activations