© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3483
    Prev
    Next
    INDEX
    Explanations

    Japanese verbs conjugated after "話"

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

    The neuron fires on East Asian (e.g. Japanese or Korean) characters.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    。
    0.69
    between
    0.63
    ことを
    0.61
    。\
    0.61
    CurrentByte
    0.61
    тину
    0.61
    存在
    0.59
    的存在
    0.58
    北方
    0.58
    嗯
    0.58
    POSITIVE LOGITS
     yolu
    0.91
    적으로
    0.91
     olmayan
    0.89
     içerisinde
    0.88
     amacı
    0.88
     önces
    0.88
     yapmak
    0.87
     edilen
    0.84
     konusu
    0.84
     sahibi
    0.83
    Activations Density 0.031%

    No Known Activations