© 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. 22-GEMMASCOPE-RES-131K
    7. 35132
    Prev
    Next
    INDEX
    Explanations

    return statement value

    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
     loup
    -0.96
     FOUND
    -0.92
     klik
    -0.91
     bruit
    -0.91
    Kama
    -0.90
     kama
    -0.90
    퐿
    -0.89
     idyl
    -0.87
    quels
    -0.86
     kust
    -0.85
    POSITIVE LOGITS
     because
    1.03
    ränken
    0.89
    ující
    0.89
    there
    0.89
     there
    0.88
     campeonato
    0.88
     hörte
    0.87
     pretože
    0.86
    适用于
    0.86
    ТА
    0.86
    Activations Density 0.002%

    No Known Activations