© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8116
    Prev
    Next
    INDEX
    Explanations

    code keywords or language constructs

    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
     was
    -1.74
    
    -1.73
    皁
    -1.72
     durumda
    -1.66
     he
    -1.57
     would
    -1.57
    。」
    -1.56
    聼
    -1.55
    ↑↑↑</
    -1.54
     insisted
    -1.52
    POSITIVE LOGITS
    .
    2.16
    /,
    1.89
     suela
    1.81
    ,’
    1.79
    ’,
    1.77
     
    1.73
    reportWebVitals
    1.70
    ⵌ
    1.70
    渕
    1.70
    転車
    1.70
    Activations Density 0.064%

    No Known Activations