© 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. 15215
    Prev
    Next
    INDEX
    Explanations

    korea and korean names

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

    This neuron activates on Korean-language text, i.e., it detects Korean words in the document.

    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
    ؛
    1.50
    ی
    1.27
    ،
    1.27
    )،
    1.22
    same
    1.20
    ات
    1.20
    ؟
    1.17
    پ
    1.14
    وف
    1.13
     یا
    1.13
    POSITIVE LOGITS
     서울
    2.36
     포
    2.31
     도
    2.28
     모든
    2.28
     국내
    2.27
     가격
    2.27
     한국
    2.23
     소
    2.22
     정
    2.20
     비
    2.20
    Activations Density 0.021%

    No Known Activations