© 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. 103133
    Prev
    Next
    INDEX
    Explanations

    numbers with units m or mg

    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
     maravillas
    -1.70
    拶
    -1.64
     感じ
    -1.57
     atracciones
    -1.56
    [];
    -1.48
     повин
    -1.48
    bình
    -1.44
    ꦠ
    -1.43
     スクール
    -1.43
    鵰
    -1.41
    POSITIVE LOGITS
    '
    1.91
    /
    1.73
    +
    1.63
    8
    1.58
    1
    1.54
    =
    1.46
    [
    1.46
    :
    1.37
    )
    1.35
    4
    1.34
    Activations Density 0.058%

    No Known Activations