© 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. 6802
    Prev
    Next
    INDEX
    Explanations

    Closing punctuation and symbols

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

    This neuron detects parenthetical asides, i.e. text enclosed in or marked by parentheses.

    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
    （
    1.95
     (
    1.88
    (
    1.63
     （
    1.60
    ﹙
    1.30
     $($
    1.20
     ("
    1.16
    ！（
    1.16
     („
    1.15
    ($
    1.14
    POSITIVE LOGITS
     ፣
    0.69
     אבל
    0.66
     '['
    0.66
    ）.
    0.66
     Anyways
    0.65
     :
    0.63
     ,
    0.63
    ］
    0.63
     ؛
    0.62
    ）,
    0.61
    Activations Density 0.283%

    No Known Activations