© 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. 3575
    Prev
    Next
    INDEX
    Explanations

    A is followed by philosopher or cat

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

    The neuron fires strongly on standalone, sentence‐initial articles or discourse markers (like “A,” “An,” or “No”) that introduce new points or list items.

    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
    apply
    0.58
    對
    0.56
    ㅂ
    0.54
    MATCH
    0.51
    राक
    0.50
    챱
    0.50
    展示
    0.49
    不同
    0.49
    WHIT
    0.49
    予
    0.49
    POSITIVE LOGITS
     بسیاری
    0.94
    多く
    0.83
     plupart
    0.80
     человек
    0.78
     Многие
    0.78
     사람은
    0.78
     사람이
    0.77
     רבים
    0.77
     muchas
    0.76
     exemplos
    0.76
    Activations Density 0.223%

    No Known Activations