© 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. 34-GEMMASCOPE-RES-131K
    7. 2679
    Prev
    Next
    INDEX
    Explanations

    Simon followed by names

    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_34/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
    格外
    -0.74
    みたいです
    -0.73
     Siberian
    -0.69
     الاف
    -0.65
    rya
    -0.65
    тивного
    -0.65
    πο
    -0.64
     recht
    -0.64
    clamp
    -0.63
    gera
    -0.63
    POSITIVE LOGITS
     nowrap
    0.89
     saken
    0.79
    ,,,,
    0.78
     baffle
    0.77
    ності
    0.76
    вления
    0.76
    notifyListeners
    0.76
     Parte
    0.75
     Spons
    0.73
    fehlungen
    0.73
    Activations Density 0.092%

    No Known Activations