© 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. 12838
    Prev
    Next
    INDEX
    Explanations

    code statement terminators

    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
     deseja
    -0.93
     also
    -0.87
    "
    -0.86
    ног
    -0.84
    «
    -0.84
    Image
    -0.83
    НОЕ
    -0.83
    @
    -0.82
    /
    -0.82
    Imagem
    -0.82
    POSITIVE LOGITS
    ()]);
    1.12
     épaules
    1.00
    .$_
    0.96
    AIzaSy
    0.92
    }]);
    0.91
    endwhile
    0.90
    anian
    0.89
     allerlei
    0.88
     genoux
    0.87
    肟
    0.87
    Activations Density 0.001%

    No Known Activations