© 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. 1724
    Prev
    Next
    INDEX
    Explanations

    Japanese grammatical endings

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

    The neuron strongly activates on sequences of Korean (Hangul) characters (i.e. non-Latin script segments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    text written in Korean or Japanese languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal sentence endings in Korean and Japanese text (polite/honorific register).

    oai_token-act-pair · gpt-5Triggered 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
     க்கு
    0.81
    对着
    0.76
     লইয়া
    0.70
    விற்கு
    0.68
     dowol
    0.68
    是谁
    0.67
    厛
    0.65
    における
    0.64
     pptd
    0.64
    த்திற்கு
    0.64
    POSITIVE LOGITS
     Fakat
    0.89
     Nhưng
    0.84
     하지만
    0.81
     mutta
    0.79
     그러나
    0.79
     fakat
    0.78
     Поэтому
    0.77
    하지만
    0.73
     물론
    0.72
     Và
    0.71
    Activations Density 0.002%

    No Known Activations