© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2348
    Prev
    Next
    INDEX
    Explanations

    comment directives or keywords

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

    The neuron detects comment‐style markers and keywords in code (e.g., “//”, “#”, “TODO”, “FIXME”).

    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_24_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
    <strong>
    1.00
    <b>
    0.99
    .
    0.79
    -
    0.77
    wood
    0.76
    ball
    0.75
    World
    0.75
    Caribbean
    0.75
    (
    0.73
    ;
    0.73
    POSITIVE LOGITS
     eslint
    1.44
     初始化
    1.25
     定义
    1.13
     FIXME
    1.08
     Для
    1.06
     Untuk
    1.06
     用于
    1.05
     Initialize
    1.05
     ใช้
    1.05
     TODO
    1.04
    Activations Density 0.004%

    No Known Activations