© 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. 100008
    Prev
    Next
    INDEX
    Explanations

    brit and brittany

    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
    řízen
    -2.97
    
    -2.95
    閙
    -2.92
     pitiful
    -2.89
     ominous
    -2.88
     інші
    -2.83
     avenues
    -2.77
    <bos>
    -2.77
    ⏑
    -2.72
     ň
    -2.69
    POSITIVE LOGITS
    1
    2.89
    k
    2.77
    S
    2.70
    后
    2.69
     και
    2.59
    v
    2.58
    and
    2.56
    鯓
    2.45
     FROM
    2.44
    3
    2.39
    Activations Density 0.002%

    No Known Activations