© 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. 99392
    Prev
    Next
    INDEX
    Explanations

    take part in

    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
    ’
    -3.02
    '
    -2.61
    ↵
    -2.47
    <
    -2.20
     beinahe
    -2.14
     ständig
    -2.03
     vollkommen
    -1.98
     rígido
    -1.96
     allmäh
    -1.91
     energética
    -1.91
    POSITIVE LOGITS
     Of
    2.31
     of
    2.16
     ``
    1.96
    丏
    1.95
    ?"
    1.92
     revolución
    1.91
    
    1.89
    TemporalType
    1.88
     -
    1.88
    先天
    1.87
    Activations Density 0.003%

    No Known Activations