© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33192
    Prev
    Next
    INDEX
    Explanations

    headings and lists

    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
     गरे
    -0.80
     лопа
    -0.78
     Retard
    -0.77
    Articulo
    -0.77
    Ху
    -0.76
     suceso
    -0.76
    쌈
    -0.75
    NumOf
    -0.73
    Уважа
    -0.73
    Прият
    -0.73
    POSITIVE LOGITS
     Oregon
    0.93
    trino
    0.93
     Shasta
    0.92
     Spokane
    0.90
    jaci
    0.90
    Oregon
    0.82
     tener
    0.79
    niger
    0.77
     salmon
    0.76
    ForRow
    0.76
    Activations Density 0.004%

    No Known Activations