© 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. 9881
    Prev
    Next
    INDEX
    Explanations

    Japanese polite endings

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

    The neuron sharply activates on non-Latin script characters (e.g. Chinese/Japanese/Korean ideographs or Hangul) in the text.

    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
    이다
    0.77
     아니다
    0.74
    난다
    0.73
    깬
    0.68
    이었다
    0.67
     같다
    0.65
    そうだ
    0.65
    이라고
    0.65
    였다
    0.65
    Turns
    0.65
    POSITIVE LOGITS
     Ihrem
    0.58
     您
    0.57
     Ihnen
    0.56
     abhiv
    0.55
     村
    0.55
    您
    0.55
    您的
    0.54
     Ihres
    0.54
    昉
    0.54
     Produced
    0.54
    Activations Density 0.016%

    No Known Activations