© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8331
    Prev
    Next
    INDEX
    Explanations

    qué es

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

    The neuron is triggered by foreign (non-English) words—especially Romance-language tokens with accents or unusual 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
     Нью
    0.64
     комплекс
    0.62
     زیرا
    0.61
     комплект
    0.61
     чтобы
    0.61
     Ново
    0.61
     Ц
    0.60
     ブラ
    0.60
     refracted
    0.59
     הד
    0.59
    POSITIVE LOGITS
     se
    1.63
     się
    1.03
     își
    0.98
     се
    0.95
     zich
    0.92
     estava
    0.90
    Se
    0.86
     sich
    0.86
     Se
    0.84
     si
    0.82
    Activations Density 0.042%

    No Known Activations