© 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. 128343
    Prev
    Next
    INDEX
    Explanations

    Emphatic punctuation

    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
     is
    -1.56
     畫
    -1.48
     same
    -1.45
    *{-
    -1.45
     can
    -1.43
    一起来
    -1.39
    ">'+
    -1.38
    avano
    -1.38
     and
    -1.38
    当時
    -1.37
    POSITIVE LOGITS
    ↵
    1.52
     „
    1.50
    馅
    1.43
    {
    1.41
    ва
    1.41
    weilen
    1.41
    шка
    1.38
     כבר
    1.37
     binatang
    1.37
    ūros
    1.35
    Activations Density 0.032%

    No Known Activations