© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7400
    Prev
    Next
    INDEX
    Explanations

    programming import statements

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

    This neuron activates on programming‐style tokens—identifiers like library/module names, file paths, URLs, and version numbers typically found in code or build‐tool output.

    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
     Vikram
    0.64
     ഓ
    0.62
     डेवल
    0.61
     collider
    0.57
    ക്ക്‌
    0.55
     Scandin
    0.55
     Jekyll
    0.55
     只
    0.54
     コンパクト
    0.54
     arugula
    0.54
    POSITIVE LOGITS
    צור
    0.66
    bel
    0.64
    sizer
    0.59
    iran
    0.57
    tema
    0.55
    Exports
    0.55
    elage
    0.55
    sprintf
    0.54
    exports
    0.53
    rophy
    0.53
    Activations Density 0.000%

    No Known Activations