© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8982
    Prev
    Next
    INDEX
    Explanations

    solving problems and providing answers

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

    The neuron fires most strongly on words that appear at the beginnings of new sentences or topical segments.

    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
     oncology
    0.62
     nightmare
    0.60
     روح
    0.59
     famílias
    0.58
    4
    0.58
     وزارة
    0.57
     genética
    0.57
    人文
    0.57
     西
    0.57
    जागरण
    0.56
    POSITIVE LOGITS
    做事
    1.03
    办事
    1.00
     совер
    0.97
     accomplishing
    0.95
     inconven
    0.90
     sesuatu
    0.90
    igenschaft
    0.89
     انجام
    0.88
     aquello
    0.87
     действие
    0.86
    Activations Density 1.014%

    No Known Activations