© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13714
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    The neuron strongly activates on numeric tokens—especially numbers enclosed in parentheses or similar list/citation markers.

    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
     one
    0.52
     II
    0.52
    0.51
     c
    0.49
     III
    0.48
     Jr
    0.48
     Bird
    0.48
     zweite
    0.48
     Kembali
    0.48
     kembali
    0.48
    POSITIVE LOGITS
    ۵
    0.59
    ༧
    0.57
    ३
    0.55
    ７
    0.55
    ６
    0.54
    ８
    0.53
    ७
    0.52
    ۶
    0.52
    ５
    0.51
    ９
    0.50
    Activations Density 0.037%

    No Known Activations