© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1749
    Prev
    Next
    INDEX
    Explanations

    mathematics and science education

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

    The neuron is sensitive to bibliographic citations or textbook reference phrases (e.g. author names, book titles, edition mentions).

    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_24_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
    情報を
    0.56
    terrain
    0.55
    contours
    0.55
    territ
    0.54
    内に
    0.54
    によって
    0.53
    끓
    0.52
    地に
    0.51
    갱
    0.50
    traffic
    0.50
    POSITIVE LOGITS
     สอน
    0.77
     الرياضيات
    0.69
     수업
    0.66
     Sophomore
    0.66
     Algebra
    0.64
     ครู
    0.64
     Mathematics
    0.63
     Lecture
    0.63
     GCSE
    0.63
     coursework
    0.62
    Activations Density 0.001%

    No Known Activations