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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41222
    Prev
    Next
    INDEX
    Explanations

    public and private keywords in code

    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_10/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
     an
    -1.54
    esomeness
    -1.44
     and
    -1.39
     going
    -1.36
    这时
    -1.34
     then
    -1.31
     on
    -1.31
     during
    -1.30
    ogical
    -1.30
    ulence
    -1.29
    POSITIVE LOGITS
     asociados
    1.54
     μαζί
    1.52
    薗
    1.50
     весьма
    1.44
     createSprite
    1.43
    營業時間
    1.43
    تحميل
    1.41
     kısa
    1.41
    超過
    1.41
    Dimensioni
    1.41
    Activations Density 0.034%

    No Known Activations