© 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. 21212
    Prev
    Next
    INDEX
    Explanations

    Chinese names and titles

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

    The neuron activates on Chinese personal names.

    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
    ，，
    -1.59
    n
    -1.36
    donde
    -1.36
    跸
    -1.34
    d
    -1.33
    ௅
    -1.28
    賅
    -1.28
    つける
    -1.27
    蔟
    -1.23
    鏐
    -1.23
    POSITIVE LOGITS
     {
    1.71
    .”
    1.58
     */
    1.55
    щита
    1.54
     $("<
    1.44
     \
    1.43
     проведения
    1.31
    iffance
    1.31
    ”
    1.30
     (
    1.28
    Activations Density 0.151%

    No Known Activations