© 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. 66502
    Prev
    Next
    INDEX
    Explanations

    in [location or topic]

    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
    了不少
    -1.43
     and
    -1.34
     but
    -1.05
     not
    -1.05
    了许多
    -0.97
     tran
    -0.92
    WEBPACK
    -0.91
    了什么
    -0.87
     a
    -0.87
    了很多
    -0.85
    POSITIVE LOGITS
     they
    1.61
     we
    1.57
     there
    1.52
     you
    1.45
     utilisez
    1.17
     perpé
    1.16
     fonctionnent
    1.13
    SALUD
    1.09
     bénéficient
    1.09
     dirait
    1.09
    Activations Density 0.081%

    No Known Activations