© 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. 9644
    Prev
    Next
    INDEX
    Explanations

    thai script with other languages

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

    The neuron strongly activates on Thai-script character sequences, i.e. it’s detecting Thai-language tokens.

    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
     大人
    0.55
    iding
    0.55
     माता
    0.53
     特に
    0.52
     متابعي
    0.51
    ﺟ
    0.50
     بتوان
    0.50
    \<^
    0.50
    üst
    0.49
     साउंड
    0.49
    POSITIVE LOGITS
    ัญญา
    0.58
    ุณ
    0.55
    ัญ
    0.55
    ภา
    0.54
    ิ
    0.52
     cleaner
    0.52
     berbahaya
    0.52
    พน
    0.51
    cubic
    0.50
    small
    0.50
    Activations Density 0.003%

    No Known Activations