© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58600
    Prev
    Next
    INDEX
    Explanations

    latex document class

    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
     will
    -1.93
     in
    -1.89
     to
    -1.80
     for
    -1.74
     from
    -1.66
     as
    -1.63
    </h2>
    -1.60
     it
    -1.60
     when
    -1.56
     by
    -1.55
    POSITIVE LOGITS
    峮
    1.63
    gemeente
    1.53
    鲩
    1.52
     "}";
    1.52
     uporab
    1.51
    hängig
    1.51
    揠
    1.49
     ';
    
    1.48
    WITHOUT
    1.48
    ější
    1.48
    Activations Density 0.005%

    No Known Activations