© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84172
    Prev
    Next
    INDEX
    Explanations

    doubles, double up, double-life

    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
    <bos>
    -1.94
     originalmente
    -1.70
     previamente
    -1.54
    または
    -1.50
     vagy
    -1.44
    ⸫
    -1.42
     supuestamente
    -1.42
    dubai
    -1.41
     
    -1.41
    dbContext
    -1.37
    POSITIVE LOGITS
    m
    1.97
    k
    1.77
     also
    1.44
     ممکن
    1.43
    //
    1.42
    b
    1.41
    饪
    1.39
     للس
    1.36
    有無
    1.36
    ử
    1.34
    Activations Density 0.008%

    No Known Activations