© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103579
    Prev
    Next
    INDEX
    Explanations

    responding or fighting back

    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
     intricate
    -2.17
     there
    -1.85
    '
    -1.83
     adequate
    -1.77
     ostensibly
    -1.72
     in
    -1.71
     this
    -1.70
    (
    -1.69
    P
    -1.68
    你和
    -1.67
    POSITIVE LOGITS
    cún
    2.28
    他的
    2.05
    
    1.90
    
    1.88
    咴
    1.82
     ไม่
    1.80
     فقط
    1.80
     uniquement
    1.77
     Pristup
    1.77
     sélectionné
    1.74
    Activations Density 0.007%

    No Known Activations