© 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. 22-GEMMASCOPE-RES-131K
    7. 27097
    Prev
    Next
    INDEX
    Explanations

    formula for calculation

    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_22/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
    𞤤
    -3.31
    
    -2.95
    𞤢
    -2.91
    pulseira
    -2.86
    "
    -2.63
    簠
    -2.61
    pecabe
    -2.58
    {
    -2.48
    jaqueta
    -2.47
     unſ
    -2.42
    POSITIVE LOGITS
    !”
    3.55
    —“
    2.91
    “
    2.80
    ?”
    2.77
    呖
    2.73
    ”
    2.69
    .”
    2.69
    —”
    2.63
    ”,
    2.58
    紲
    2.48
    Activations Density 0.009%

    No Known Activations