© 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. 12187
    Prev
    Next
    INDEX
    Explanations

    parenthesized letters (A, B, C, D)

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

    The neuron activates on formal legal citations—article, section, paragraph, and statute numbers referencing laws or regulations.

    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
     பாபிலோ
    0.59
     /ˈ
    0.53
     recovered
    0.48
    즌
    0.48
     SES
    0.47
     Chapter
    0.46
     violently
    0.46
     የወ
    0.45
     (§
    0.45
    ⟧
    0.44
    POSITIVE LOGITS
    b
    0.83
     b
    0.81
    (
    0.80
    .(
    0.75
    \(
    0.72
    "(
    0.71
     subparagraph
    0.70
    a
    0.70
    ａ
    0.70
    ⑵
    0.70
    Activations Density 0.144%

    No Known Activations