© 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. 6124
    Prev
    Next
    INDEX
    Explanations

    European countries and guidelines

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

    The neuron activates on mentions of geographic place names (countries, regions, and major locations).

    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
     Arizona
    0.90
    0.86
     Oklahoma
    0.79
     Florida
    0.77
     California
    0.75
     Michigan
    0.75
    you
    0.74
    1
    0.74
     Kansas
    0.73
     Marketplace
    0.71
    POSITIVE LOGITS
     և
    1.35
     ਅਤੇ
    1.28
     եւ
    1.28
     και
    1.26
     и
    1.21
     ಮತ್ತು
    1.20
     һәм
    1.20
    および
    1.17
     καὶ
    1.16
     এবং
    1.11
    Activations Density 0.001%

    No Known Activations