© 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. 67742
    Prev
    Next
    INDEX
    Explanations

    html unordered lists

    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
    Such
    -2.03
    A
    -1.93
    .
    -1.77
    Its
    -1.77
    如果
    -1.73
    [
    -1.71
    if
    -1.69
    Well
    -1.68
     
    -1.62
    O
    -1.53
    POSITIVE LOGITS
     kommentar
    1.91
     процессе
    1.78
    䊐
    1.71
     phénom
    1.71
    蚨
    1.70
    Ведущий
    1.69
     garota
    1.68
    ⢅
    1.66
    炻
    1.65
    Причины
    1.64
    Activations Density 0.010%

    No Known Activations