© 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. 40883
    Prev
    Next
    INDEX
    Explanations

    purpose or characteristic

    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
     for
    -2.03
     This
    -1.91
     into
    -1.71
     now
    -1.69
    ;
    -1.63
    :
    -1.55
     noiva
    -1.48
     up
    -1.43
     in
    -1.43
     senhora
    -1.41
    POSITIVE LOGITS
    呖
    1.86
    استفاده
    1.73
     случаях
    1.66
    纥
    1.63
    
    1.63
    tabol
    1.62
    колко
    1.61
     butik
    1.60
     dagens
    1.59
     كيفية
    1.59
    Activations Density 0.011%

    No Known Activations