© 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. 4171
    Prev
    Next
    INDEX
    Explanations

    full or reduced

    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
     sám
    -0.87
    告别
    -0.86
    ampingi
    -0.80
    綁
    -0.80
    是怎么
    -0.79
    Ejemplos
    -0.79
     작업
    -0.77
    Estudi
    -0.77
    Estar
    -0.76
    criture
    -0.76
    POSITIVE LOGITS
     full
    2.30
    full
    1.66
    Full
    1.42
     peł
    1.31
     Full
    1.17
    FULL
    1.16
     FULL
    1.14
     strength
    1.13
     penuh
    1.09
     מלא
    1.03
    Activations Density 0.044%

    No Known Activations