© 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. 11515
    Prev
    Next
    INDEX
    Explanations

    France

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

    The neuron is strongly activated by French‐language tokens—especially formal legal/administrative terms and words with accented characters.

    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
     Greeley
    0.80
     malay
    0.76
     BYU
    0.75
     MSU
    0.75
     Roswell
    0.75
     Horton
    0.73
     Aś
    0.73
    昱
    0.72
     QuickBooks
    0.72
     Asheville
    0.71
    POSITIVE LOGITS
    フランス
    2.88
     فرنسا
    2.78
    法國
    2.75
    France
    2.73
     France
    2.67
    法国
    2.67
     프랑
    2.67
    French
    2.66
     الفرنس
    2.66
     フランス
    2.63
    Activations Density 0.808%

    No Known Activations