© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10373
    Prev
    Next
    INDEX
    Explanations

    running FastAPI app

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

    The neuron activates on programming‐oriented text—API names, code identifiers, protocol terms, and other technical jargon in documentation.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     jTextField
    0.59
    icester
    0.57
    algar
    0.57
     जुड़े
    0.55
    ⌣
    0.55
    orters
    0.55
    >\
    0.55
     chargers
    0.54
    LCD
    0.53
     splashes
    0.53
    POSITIVE LOGITS
    tsy
    0.58
    攣
    0.56
    拧
    0.55
     procedure
    0.54
     규
    0.53
     vas
    0.51
     vasocon
    0.51
     procedures
    0.49
     procedimientos
    0.49
     Greenhouse
    0.49
    Activations Density 0.002%

    No Known Activations