© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93234
    Prev
    Next
    INDEX
    Explanations

    copyright statements

    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
     clé
    -1.04
     pneus
    -0.98
    Очень
    -0.98
     Thé
    -0.97
    Scripts
    -0.97
     rất
    -0.93
    ابی
    -0.93
    viii
    -0.91
    diger
    -0.90
    ovým
    -0.90
    POSITIVE LOGITS
    UnitTesting
    1.10
    chandise
    1.06
     didn
    1.05
    谥
    1.02
     was
    1.02
    这件事情
    0.99
     darauf
    0.98
     xay
    0.98
     games
    0.97
     trastornos
    0.96
    Activations Density 0.002%

    No Known Activations