© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112650
    Prev
    Next
    INDEX
    Explanations

    Japanese questions and proper nouns

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

    The neuron fires on Japanese question/wh-words (interrogative terms such as “何,” “どこ,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    有
    -2.56
    ers
    -2.55
     nimmer
    -2.52
    sandalia
    -2.45
     schonmal
    -2.38
     miljoner
    -2.38
    鼇
    -2.38
    有不
    -2.33
     jezt
    -2.27
     habido
    -2.25
    POSITIVE LOGITS
    </em>
    3.03
     It
    2.98
    {
    2.48
    ☫
    2.30
    伫
    2.27
     größere
    2.20
    不觉
    2.19
    阖
    2.16
    蛰
    2.13
     opted
    2.11
    Activations Density 0.000%

    No Known Activations