© 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. 69908
    Prev
    Next
    INDEX
    Explanations

    bab words

    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
    cliente
    -0.75
    Departamento
    -0.73
    湄
    -0.72
     cliente
    -0.69
    ͡
    -0.69
    ା
    -0.69
    𝐽
    -0.68
    谘
    -0.68
     좋
    -0.67
    QList
    -0.67
    POSITIVE LOGITS
    inté
    1.05
    мно
    0.78
     lumières
    0.77
    韁
    0.76
    yoto
    0.76
    往前
    0.75
     ativar
    0.75
     clicar
    0.74
    chemia
    0.73
     babi
    0.73
    Activations Density 0.022%

    No Known Activations