© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14383
    Prev
    Next
    INDEX
    Explanations

    diagnosis and intelligence

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

    The neuron fires on semantically rich content words—especially longer, descriptive nouns, verbs, and adjectives—rather than on function words.

    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_24_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
     orthodontic
    0.75
     бизнеса
    0.73
    тифика
    0.71
     qualific
    0.71
     notion
    0.69
     trench
    0.69
     fission
    0.68
    섭
    0.67
    Ship
    0.66
     सैनिक
    0.66
    POSITIVE LOGITS
    ıya
    0.99
    ﯿ
    0.93
    ı
    0.90
     ชม
    0.88
    ია
    0.81
    ﺘ
    0.81
    í
    0.80
    ası
    0.77
    ﯽ
    0.77
    ኡ
    0.76
    Activations Density 0.000%

    No Known Activations