© 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. 7538
    Prev
    Next
    INDEX
    Explanations

    European or related to Europe

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

    The neuron strongly activates on occurrences of “European” (and closely related EU-region terms), i.e. references to Europe or European institutions.

    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
     राष्ट्रीय
    0.62
    lim
    0.61
     ملی
    0.60
    каў
    0.59
    dpi
    0.58
    周期
    0.57
    全国
    0.56
     त
    0.56
    isable
    0.56
    ing
    0.55
    POSITIVE LOGITS
     continent
    1.00
     Union
    0.80
     continente
    0.78
    大陸
    0.73
     Continent
    0.71
    大陆
    0.69
    Union
    0.69
    ኀ
    0.65
    continent
    0.63
     continents
    0.62
    Activations Density 0.102%

    No Known Activations