© 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. 34-GEMMASCOPE-RES-131K
    7. 97833
    Prev
    Next
    INDEX
    Explanations

    japanese names and words

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

    The neuron detects romanized Japanese words and names (e.g. song titles, band names, and other Japanese proper nouns written in Latin script).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     япон
    -1.02
    Verses
    -0.98
    footnotesize
    -0.98
     Opto
    -0.96
     naszej
    -0.92
     Nhật
    -0.91
     Japón
    -0.91
     Япо
    -0.91
    իա
    -0.91
    kontrolle
    -0.90
    POSITIVE LOGITS
     no
    1.06
    !!:
    1.00
    ashi
    1.00
    👋
    0.95
    ī
    0.95
     desu
    0.94
    
    0.94
     Kette
    0.93
     sør
    0.93
    WL
    0.93
    Activations Density 0.050%

    No Known Activations