© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103906
    Prev
    Next
    INDEX
    Explanations

    Quantification of

    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
     Bekasi
    -0.97
     zoll
    -0.79
     dipin
    -0.77
     loren
    -0.74
    吒
    -0.74
     dollars
    -0.73
     gql
    -0.71
     ballast
    -0.69
     chré
    -0.68
     wymiar
    -0.68
    POSITIVE LOGITS
    ciais
    0.86
    UC
    0.85
     EU
    0.82
    Ammonia
    0.82
    scaleX
    0.82
     КО
    0.81
    shadowOffset
    0.81
     €
    0.80
    valuer
    0.80
    artments
    0.79
    Activations Density 0.013%

    No Known Activations