© 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. 60060
    Prev
    Next
    INDEX
    Explanations

    Unity code, technical context

    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
    andt
    -0.79
     fundas
    -0.75
    reeze
    -0.73
    ЕНЬ
    -0.71
    ườn
    -0.71
     Revel
    -0.71
     効果
    -0.69
    ท์
    -0.69
    IVIDUAL
    -0.69
    nextProps
    -0.68
    POSITIVE LOGITS
    NickName
    0.85
    fileID
    0.82
     periódicos
    0.81
    ใบ
    0.79
    migrationBuilder
    0.79
    Happiness
    0.77
     урок
    0.77
     Maler
    0.77
     barrica
    0.77
     calificación
    0.76
    Activations Density 0.008%

    No Known Activations