© 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. 22-GEMMASCOPE-RES-131K
    7. 128556
    Prev
    Next
    INDEX
    Explanations

    coordinates and labels

    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_22/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
    Leírás
    -1.11
     montrant
    -0.94
    zwald
    -0.91
    previously
    -0.90
    formerly
    -0.89
    Conseil
    -0.88
     verdo
    -0.87
    chenta
    -0.87
    viene
    -0.86
     sporad
    -0.86
    POSITIVE LOGITS
     quelli
    0.98
    unyai
    0.97
    gráfico
    0.94
     Entscheidungen
    0.94
    cnbc
    0.88
    หลัง
    0.86
     schönen
    0.86
    ulance
    0.86
    ższy
    0.86
     esso
    0.85
    Activations Density 0.030%

    No Known Activations