© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57561
    Prev
    Next
    INDEX
    Explanations

    multiple languages

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

    This neuron activates on sequences of non-Latin (Unicode) characters, i.e. tokens in scripts like Cyrillic, Japanese, Arabic, Thai, 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
     there
    -1.32
    ゎ
    -1.31
    guitarra
    -1.30
     宝宝
    -1.29
    就是这样
    -1.27
     вони
    -1.25
    número
    -1.23
    彼らは
    -1.23
     бывает
    -1.21
    このように
    -1.21
    POSITIVE LOGITS
     Karakter
    1.41
    lised
    1.38
     Baş
    1.32
    tened
    1.30
    ~”
    1.28
    ?”
    1.28
    向了
    1.27
    <>
    
    1.27
     Teknik
    1.26
    …,
    1.25
    Activations Density 0.049%

    No Known Activations