© 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. 72483
    Prev
    Next
    INDEX
    Explanations

    catching exceptions

    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
     certainly
    -1.60
    –>
    -1.55
     own
    -1.55
    の問題
    -1.53
    —–
    -1.51
    <strong>
    -1.51
    就是
    -1.50
    椟
    -1.48
    仨
    -1.46
     termed
    -1.45
    POSITIVE LOGITS
    ᳝
    1.64
     высоты
    1.63
    tisgarh
    1.62
    hláš
    1.57
    телно
    1.57
     dekol
    1.56
     войны
    1.53
     sezonu
    1.52
     مجلسی
    1.52
     красиво
    1.52
    Activations Density 0.004%

    No Known Activations