© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8802
    Prev
    Next
    INDEX
    Explanations

    Vietnamese language and culture

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

    The neuron detects Vietnamese-language text segments.

    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
    وف
    1.16
    ًا
    1.14
    ال
    1.13
    and
    1.13
    الم
    1.13
    of
    1.08
     له
    1.08
    ما
    1.06
    R
    1.03
    op
    1.02
    POSITIVE LOGITS
     nhiều
    2.05
     giúp
    1.90
     khi
    1.89
     như
    1.87
     những
    1.86
     cùng
    1.84
     rất
    1.84
     hệ
    1.84
     thấy
    1.83
     tất
    1.81
    Activations Density 0.057%

    No Known Activations