© 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. 66
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on tokens written in non-Latin scripts (e.g. Korean, Japanese, Hindi).

    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
    此外
    0.45
    Denote
    0.40
    Whitney
    0.38
    悧
    0.38
    Ма
    0.38
    Miscellaneous
    0.37
    С
    0.37
    Ко
    0.37
    Та
    0.37
    Optical
    0.37
    POSITIVE LOGITS
     çok
    0.54
     artık
    0.51
     bugün
    0.51
     daha
    0.51
     조금
    0.51
     farklı
    0.50
     더욱
    0.50
     herkes
    0.49
     tamamen
    0.49
     rahat
    0.49
    Activations Density 0.023%

    No Known Activations