© 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. 112585
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ญี่ป
    -1.95
    砹
    -1.89
    ༀ
    -1.80
    沇
    -1.77
    쑨
    -1.77
    
    -1.68
     inalámb
    -1.66
    鈑
    -1.63
     unprecedented
    -1.62
     in
    -1.59
    POSITIVE LOGITS
    ();
    1.98
     και
    1.90
    而
    1.85
    </strong>
    1.83
     và
    1.82
     و
    1.77
    </h4>
    1.77
    澌
    1.75
    ">
    1.72
    s
    1.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.