© 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. 39487
    Prev
    Next
    INDEX
    Explanations

    lists and legal citations

    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
    {
    -2.39
     geda
    -1.78
     tional
    -1.77
     ,.
    -1.60
     hlavy
    -1.59
     jednod
    -1.55
     izvē
    -1.48
    is
    -1.48
    ar
    -1.46
     unfolding
    -1.46
    POSITIVE LOGITS
    Préparation
    1.63
    Опис
    1.56
     حتی
    1.50
     sogar
    1.44
    
    1.43
    Pratique
    1.42
    راهيم
    1.41
     who
    1.41
    Médaille
    1.41
    ਗ਼
    1.40
    Activations Density 0.007%

    No Known Activations