© 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. 85790
    Prev
    Next
    INDEX
    Explanations

    completing tasks or actions

    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
     that
    -1.66
     there
    -1.56
     時間
    -1.38
     autorizado
    -1.36
     tradicionais
    -1.34
     recentes
    -1.34
    えっ
    -1.31
     necessárias
    -1.31
     mogelijkheid
    -1.27
    遠慮
    -1.25
    POSITIVE LOGITS
    我在
    1.31
    接近
    1.29
    当初
    1.27
    ísticos
    1.27
    就
    1.23
     “¿
    1.20
    、
    1.17
    早
    1.16
     ۱۸
    1.16
    使
    1.16
    Activations Density 0.178%

    No Known Activations