© 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. 6022
    Prev
    Next
    INDEX
    Explanations

    book titles and concepts

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

    The neuron strongly activates on capitalized content words that appear in book or article titles (i.e. title-cased keywords in bibliographic references).

    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
    ק
    0.63
    갇
    0.61
    wohner
    0.57
    괜
    0.57
    так
    0.56
    від
    0.56
    сик
    0.56
    并将
    0.55
     väldigt
    0.55
    Һ
    0.55
    POSITIVE LOGITS
     Algebras
    0.63
     Ware
    0.60
     introductory
    0.60
     スマート
    0.58
     Strategies
    0.57
     ขั้น
    0.57
     القيام
    0.57
     标准
    0.57
     Mortality
    0.56
     Needham
    0.56
    Activations Density 0.065%

    No Known Activations