© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5639
    Prev
    Next
    INDEX
    Explanations

    Python code structure

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

    The neuron fires on code tokens involved in JSON property access chains—especially when you see “json”, “results”, “item” and a numeric index in bracket notation.

    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
    (*
    0.73
     +=
    0.71
     +
    0.69
    (*(
    0.69
    ((
    0.68
    isr
    0.67
    _(
    0.62
    ())
    0.61
    ([
    0.61
     *(
    0.61
    POSITIVE LOGITS
    ()['
    0.77
    ['
    0.77
    ']['
    0.74
    "]["
    0.70
    ंच्या
    0.68
    ["
    0.66
    ')['
    0.66
    пыт
    0.64
    ]['
    0.58
     निर्देशा
    0.58
    Activations Density 0.002%

    No Known Activations