© 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. 34-GEMMASCOPE-RES-131K
    4. 92131
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

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

    The neuron consistently lights up on Chinese-language tokens (i.e. Chinese words or characters) embedded in otherwise non-Chinese 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_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
    」,
    -1.13
    ണം
    -1.05
    特定的
    -0.94
    டம்
    -0.94
    原来的
    -0.92
     DESCRIP
    -0.89
     martens
    -0.89
    ﺅ
    -0.88
     INCORPOR
    -0.88
    )$,
    -0.86
    POSITIVE LOGITS
     of
    2.06
    信息的
    1.55
     and
    1.53
    问题的
    1.30
     的
    1.21
    )’
    1.20
    数据的
    1.14
     but
    1.14
    笑的
    1.13
    들의
    1.11
    Activations Density 0.005%

    No Known Activations