© 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. 68228
    Prev
    Next
    INDEX
    Explanations

    variable name initialization

    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
     at
    -2.06
     after
    -1.87
     from
    -1.82
     by
    -1.78
     on
    -1.77
     relatively
    -1.73
     more
    -1.72
     especially
    -1.70
     an
    -1.70
     and
    -1.67
    POSITIVE LOGITS
    来讲
    1.69
     the
    1.63
     certamente
    1.48
    읗
    1.48
     制服
    1.47
     dando
    1.46
     Sistema
    1.46
     .........
    1.45
    沵
    1.43
    殽
    1.42
    Activations Density 0.030%

    No Known Activations