© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41102
    Prev
    Next
    INDEX
    Explanations

    all you

    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
     火鍋
    -1.89
    桖
    -1.80
    絰
    -1.66
     decisione
    -1.60
     acque
    -1.59
    瞜
    -1.53
    yeur
    -1.52
     fără
    -1.52
    leggen
    -1.50
    laining
    -1.49
    POSITIVE LOGITS
    ."
    2.34
     they
    2.25
    朏
    1.95
    癀
    1.83
    idopsis
    1.67
    ۔
    1.63
    ك
    1.63
    ?
    1.63
    非常好
    1.61
    たたみ
    1.59
    Activations Density 0.003%

    No Known Activations