© 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. 13999
    Prev
    Next
    INDEX
    Explanations

    tool or function descriptions

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

    The neuron fires on numeric tokens—especially percentages, measurements, and other numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ♡
    0.57
    ！”
    0.52
    Car
    0.50
    {}
    0.50
    Carr
    0.50
    乇
    0.49
    Mile
    0.48
    polished
    0.48
    ₁+
    0.48
     polished
    0.48
    POSITIVE LOGITS
    箅
    0.63
    उदा
    0.61
    बहुत
    0.59
     කෙ
    0.59
     NGF
    0.59
     semicircle
    0.59
     vicenda
    0.59
    ിക്കുന്നത്
    0.57
     steppe
    0.57
    ເຂ
    0.56
    Activations Density 0.000%

    No Known Activations