© 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. 359
    Prev
    Next
    INDEX
    Explanations

    code, programming, or biology contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    file extensions and programming syntax elements in code files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     sugars
    -0.81
     —
    -0.81
     as
    -0.80
     maine
    -0.78
    فة
    -0.78
     階
    -0.78
    ,
    -0.77
     will
    -0.77
     that
    -0.77
    小程序
    -0.75
    POSITIVE LOGITS
     commencent
    1.05
     vivent
    0.96
    hmen
    0.95
     dimulai
    0.94
    mayın
    0.93
    unhofer
    0.93
     furent
    0.92
    嫫
    0.92
     fournit
    0.92
    を探す
    0.91
    Activations Density 0.016%

    No Known Activations