© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13869
    Prev
    Next
    INDEX
    Explanations

    code syntax (json, js, python)

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

    The neuron is sensitive to mentions of programming libraries, frameworks, and API module names (e.g. Express, Mongoose, io.use, Math.random, module.hot.accept).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Nomenclature
    0.49
     냉
    0.49
    ዛ
    0.49
    𒌨
    0.49
    ध्या
    0.49
     Relations
    0.48
     Marriage
    0.48
    শান্ত
    0.48
     መን
    0.48
    eslint
    0.48
    POSITIVE LOGITS
    sep
    0.71
     sep
    0.70
     ويت
    0.55
    prototype
    0.54
    瑰
    0.54
     सीट
    0.53
    existsSync
    0.53
    インチ
    0.52
    upport
    0.51
     SEP
    0.50
    Activations Density 0.002%

    No Known Activations