© 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. 1608
    Prev
    Next
    INDEX
    Explanations

    thai consonants and syllables

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

    The main thing this neuron does is detect Thai‐language script segments (sequences of Thai 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
    ․
    0.71
     را
    0.64
     Ashram
    0.63
     egip
    0.62
     وع
    0.61
     أهم
    0.61
     değişik
    0.61
     مختلف
    0.60
    ･
    0.58
     Neend
    0.57
    POSITIVE LOGITS
    ้
    0.66
    ่
    0.64
     polynomial
    0.56
    Additive
    0.54
    Bennett
    0.52
    California
    0.50
    PerTrial
    0.50
    字符串
    0.50
    polynomial
    0.50
    Markdown
    0.50
    Activations Density 0.005%

    No Known Activations