© 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. 7425
    Prev
    Next
    INDEX
    Explanations

    countries and regions

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

    The neuron activates on place names—particularly continents, countries, and broad geographic regions.

    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
     bouts
    0.85
    FromFile
    0.78
    Η
    0.74
     admissible
    0.71
     στο
    0.70
    िका
    0.70
     Alonzo
    0.70
     Norbert
    0.68
     foreigners
    0.66
     град
    0.66
    POSITIVE LOGITS
     Selatan
    0.84
    も含
    0.83
     Serikat
    0.82
     включая
    0.80
     Tenggara
    0.77
    大哥
    0.76
    urangi
    0.75
    kezi
    0.74
    豊かな
    0.73
     সরিয়ে
    0.72
    Activations Density 0.080%

    No Known Activations