© 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. 21065
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with rm or cal symbols

    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
    pectives
    -1.63
     can
    -1.52
    ?’
    -1.38
    );
    -1.38
    Dimensões
    -1.38
    Composição
    -1.36
     kirja
    -1.33
     ряд
    -1.32
    <
    -1.31
    This
    -1.29
    POSITIVE LOGITS
    lgari
    1.64
    .
    1.42
    に行って
    1.39
    
    1.38
    スポンサーリンク
    1.37
    
    1.36
    {
    1.34
    zurück
    1.34
     conqu
    1.28
    yasi
    1.28
    Activations Density 0.001%

    No Known Activations