© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58312
    Prev
    Next
    INDEX
    Explanations

    开发, wasm, amelior, unregulated, Okanagan

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

    The neuron selectively activates on code tokens related to WebAssembly, especially the “wasm”/“wasm_bindgen” annotations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    秶
    -3.55
    𓆉
    -3.16
    鹀
    -3.09
    
    -2.84
     pérd
    -2.80
    蒹
    -2.70
    蕺
    -2.70
    畋
    -2.67
    どうしよう
    -2.67
    ﹍﹍
    -2.61
    POSITIVE LOGITS
    ↵↵
    3.63
    {
    3.42
    ."
    3.11
    }
    2.98
    [
    2.92
    •
    2.78
    ные
    2.61
    "
    2.61
    0
    2.56
    *
    2.56
    Activations Density 0.006%

    No Known Activations