© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110829
    Prev
    Next
    INDEX
    Explanations

    Japanese kanji and verb endings

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

    The neuron fires whenever it encounters Japanese script (Kanji or Kana) characters in the text.

    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
    ⛦
    -2.13
    壟
    -1.90
    濺
    -1.87
    Bakgrunns
    -1.74
     to
    -1.72
    纜
    -1.67
     berkomunikasi
    -1.66
    selbe
    -1.65
    ꨄ
    -1.62
    ⚋
    -1.62
    POSITIVE LOGITS
    {
    2.31
    ?
    2.25
     it
    1.97
     you
    1.93
     we
    1.92
    *
    1.76
     needed
    1.70
        
    1.63
     would
    1.60
            
    1.56
    Activations Density 0.004%

    No Known Activations