© 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. 7741
    Prev
    Next
    INDEX
    Explanations

    gs acronym or initial

    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
    .
    -3.11
    名古屋
    -2.73
    that
    -2.69
    jewództ
    -2.63
    sibilité
    -2.56
     That
    -2.55
    lossians
    -2.50
    ～。
    -2.48
    usahaan
    -2.42
     MINISTER
    -2.41
    POSITIVE LOGITS
    gs
    3.47
    ing
    3.41
    
    3.27
     BECAUSE
    3.02
     腕
    2.91
    a
    2.83
    y
    2.81
     stalwart
    2.73
     zwei
    2.72
    퐿
    2.69
    Activations Density 0.005%

    No Known Activations