© 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. 106500
    Prev
    Next
    INDEX
    Explanations

    words like "stoppes"

    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
    âncias
    -0.81
    mand
    -0.80
     Oro
    -0.78
    StringVar
    -0.77
    bindParam
    -0.75
     Supplementary
    -0.75
    tds
    -0.73
    ñor
    -0.72
    endant
    -0.72
     Tare
    -0.72
    POSITIVE LOGITS
    のではなく
    0.83
    感じが
    0.79
     Jetzt
    0.78
    aleg
    0.74
    Noun
    0.74
    interpreted
    0.73
     kiezen
    0.73
    ところは
    0.73
     rơi
    0.72
    高兴
    0.71
    Activations Density 0.019%

    No Known Activations