© 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. 73491
    Prev
    Next
    INDEX
    Explanations

    the size of

    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
    蛱
    -1.83
    
    -1.74
     También
    -1.73
    ſch
    -1.70
    
    -1.69
     Также
    -1.67
     Können
    -1.66
    莛
    -1.66
    ﮭ
    -1.66
     ヤ
    -1.63
    POSITIVE LOGITS
     in
    1.83
     from
    1.83
     at
    1.80
     new
    1.79
    i
    1.55
    on
    1.54
    up
    1.53
     through
    1.52
     each
    1.52
     required
    1.51
    Activations Density 0.073%

    No Known Activations