© 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. 2749
    Prev
    Next
    INDEX
    Explanations

    dialogue punctuation followed by speaker

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

    The neuron fires on end-of-sentence punctuation inside closing quotation marks (e.g. tokens like .” ?” or !”).

    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
     (
    1.26
     [
    0.98
    <sup>
    0.93
    （
    0.93
     -
    0.88
     and
    0.86
    and
    0.85
    [
    0.84
     ("
    0.83
    0.81
    POSITIVE LOGITS
    说着
    0.90
     ру
    0.88
     другом
    0.88
     він
    0.87
     спине
    0.86
     grinned
    0.85
     પાણી
    0.84
    निश्ड
    0.83
    ließen
    0.83
     ゆっくり
    0.82
    Activations Density 0.010%

    No Known Activations