© 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. 22402
    Prev
    Next
    INDEX
    Explanations

    `=` or `[` followed by `,` or `"`

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

    This neuron detects the opening square bracket that begins an array or list literal in code.

    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
     or
    -2.80
    เกง
    -2.59
     (
    -2.56
     [
    -2.53
     .
    -2.50
    สำหรับ
    -2.50
    ."
    -2.45
     \
    -2.45
     für
    -2.36
    หรือ
    -2.25
    POSITIVE LOGITS
    ほとん
    2.98
     pesso
    2.77
    そりゃ
    2.72
    ままで
    2.69
     cancelamento
    2.66
    棪
    2.63
    私には
    2.61
    筇
    2.61
    籥
    2.53
     alimente
    2.50
    Activations Density 0.001%

    No Known Activations