© 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. 66951
    Prev
    Next
    INDEX
    Explanations

    Japanese particle と

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

    This neuron detects the Japanese conditional or quotative particle “と” (and its appearances in common verb‐と combinations).

    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
    aches
    -1.65
    ㅎ
    -1.63
    Ꮸ
    -1.60
     dansk
    -1.56
    などが
    -1.55
    も
    -1.55
    lossians
    -1.54
    
    -1.53
    re
    -1.52
     unserer
    -1.50
    POSITIVE LOGITS
     もう
    1.99
    さぁ
    1.90
    <i>
    1.90
    ができます
    1.88
     However
    1.88
     staggering
    1.88
    来週
    1.88
    <blockquote>
    1.83
    久し
    1.73
    昨日は
    1.72
    Activations Density 0.001%

    No Known Activations