© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42383
    Prev
    Next
    INDEX
    Explanations

    python plots and axes

    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
    ’
    -2.20
    ization
    -1.94
    
    -1.84
    逦
    -1.80
    Ꮟ
    -1.78
    zione
    -1.77
    杲
    -1.77
     ditangkap
    -1.62
    .”
    -1.59
    ”,
    -1.58
    POSITIVE LOGITS
    \
    1.77
    汌
    1.70
     {
    1.69
     gebra
    1.69
    總是
    1.67
    热血
    1.63
    0
    1.63
     soll
    1.60
    所で
    1.60
    enablog
    1.59
    Activations Density 0.004%

    No Known Activations