© 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. 6079
    Prev
    Next
    INDEX
    Explanations

    closing syntax punctuation

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

    The neuron detects in‐text metadata and reference markers (e.g. “Figure,” “Videos,” “n.,” “posted:”) that introduce numbered citations or media labels.

    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
    {-\
    0.61
     Conjecture
    0.61
    {\
    0.60
     Question
    0.60
     Weierstrass
    0.58
    ^{\
    0.57
     ^{\
    0.57
    {\|
    0.57
     {\
    0.56
    {$\
    0.56
    POSITIVE LOGITS
    "][
    0.77
    }[
    0.77
    '][
    0.71
    )[
    0.71
    }}[
    0.71
    }(
    0.65
    ")(
    0.65
     לאחר
    0.63
    ")[
    0.63
     ৯
    0.61
    Activations Density 0.003%

    No Known Activations