© 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. 10158
    Prev
    Next
    INDEX
    Explanations

    places of commerce and service

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

    The neuron flags mentions of public commercial or exhibition venues (e.g. shops, pubs, galleries, cinemas, theatres).

    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
    Lieutenant
    0.74
    empl
    0.73
    ﺪ
    0.70
    것도
    0.70
    ן
    0.69
    禊
    0.67
    鸯
    0.66
    を発
    0.66
     Aircraft
    0.66
     لكرة
    0.64
    POSITIVE LOGITS
     shops
    1.01
     clerks
    0.96
     malls
    0.95
     bookstores
    0.95
     shelves
    0.95
     ร้าน
    0.94
     supermarkets
    0.93
     nationwide
    0.92
     দোকানে
    0.92
    门店
    0.92
    Activations Density 0.001%

    No Known Activations