© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38773
    Prev
    Next
    INDEX
    Explanations

    questions and explanations

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

    This neuron detects Japanese-language tokens (i.e. words written in Japanese scripts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。　　
    -1.95
    す
    -1.91
    すべての
    -1.89
    但这
    -1.80
    すぐに
    -1.70
    などが
    -1.70
    这让
    -1.68
    因为它
    -1.64
     contextLoads
    -1.63
    そして
    -1.61
    POSITIVE LOGITS
    Compared
    1.86
    んですよ
    1.80
    Whether
    1.72
    さぁ
    1.70
    無し
    1.68
     Whether
    1.68
    之后
    1.68
    んですか
    1.67
    んですね
    1.64
    부터
    1.64
    Activations Density 0.001%

    No Known Activations