© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 1550
    Prev
    Next
    INDEX
    Explanations

    code blocks

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

    The neuron fires on mentions of programming‐related technical jargon—especially the “StackOverflow” site name and regex/config keywords.

    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
     intramolecular
    0.70
     ­
    0.59
     Lobkovic
    0.58
    ONEDB
    0.58
    かせ
    0.56
     vacuo
    0.56
    肱
    0.55
     erneut
    0.55
     arginine
    0.55
    ケート
    0.55
    POSITIVE LOGITS
    <code>
    1.12
    <h1>
    0.90
    <h2>
    0.90
    <table>
    0.75
    <blockquote>
    0.68
    In
    0.68
    <strong>
    0.66
    <h3>
    0.66
    <sub>
    0.66
    <sup>
    0.65
    Activations Density 0.048%

    No Known Activations