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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 674
    Prev
    Next
    INDEX
    Explanations

    geo-political regions and entities

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

    The neuron detects mentions of countries, regions, or other broad geopolitical/international terms.

    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_31_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
     从
    0.37
    の
    0.37
     なさい
    0.36
     Mitarbeiter
    0.36
     Как
    0.36
     Là
    0.36
    之
    0.35
     か
    0.34
     Consultado
    0.34
     当前
    0.34
    POSITIVE LOGITS
     governments
    0.56
     waterways
    0.54
     cuisine
    0.48
     shores
    0.48
    orsz
    0.48
     coastline
    0.47
     প্রেক্ষিতে
    0.47
     hegemony
    0.47
     universities
    0.46
     sensibilities
    0.46
    Activations Density 0.628%

    No Known Activations