© 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. 6473
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis or comma

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

    The neuron strongly activates on multi‐digit numeric tokens (especially four‐digit years) typically used as citation dates.

    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
    。
    0.57
    ‍
    0.53
    。（
    0.52
    giz
    0.52
    。\
    0.52
    。“
    0.52
    。《
    0.52
    Bạn
    0.50
    。[
    0.50
    。『
    0.50
    POSITIVE LOGITS
     posits
    0.52
     hük
    0.50
     காலத்தில்
    0.48
     condiments
    0.48
     とする
    0.48
     гульнявыя
    0.48
    arrerol
    0.48
     utterance
    0.47
     risc
    0.47
    ylob
    0.47
    Activations Density 0.011%

    No Known Activations