© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4697
    Prev
    Next
    INDEX
    Explanations

    business sector industry domain

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

    The neuron fires strongly on tokens naming broad categories or domains—especially “sector,” “region,” “area,” or similar labels identifying an industry, geographic, or organizational category.

    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
    ⺝
    0.68
     позволя
    0.68
    ানির
    0.62
    老婆
    0.60
    ปล่อย
    0.60
    পত্র
    0.60
     pairing
    0.60
     ਜਾਂ
    0.59
    ugging
    0.58
     sogen
    0.57
    POSITIVE LOGITS
    Этот
    0.70
    İ
    0.64
    ال
    0.63
    constraints
    0.63
     فيما
    0.62
    verwaltung
    0.60
     Kegiatan
    0.60
     فى
    0.59
     Этот
    0.59
    xml
    0.58
    Activations Density 0.000%

    No Known Activations