© 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. 22-GEMMASCOPE-RES-131K
    7. 9763
    Prev
    Next
    INDEX
    Explanations

    Chinese words indicating specific actions or states

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

    The neuron fires most strongly on individual CJK (Chinese/Japanese/Kanji) characters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    谞
    -1.83
    沇
    -1.80
     of
    -1.77
     शुर
    -1.69
     in
    -1.68
    ဴ
    -1.67
    瑧
    -1.64
    ஂ
    -1.64
    ༀ
    -1.61
    籐
    -1.60
    POSITIVE LOGITS
     véhic
    1.99
     rejoint
    1.81
     rassemb
    1.77
    鷽
    1.77
     afspraak
    1.66
     isoliert
    1.66
    俛
    1.66
     publicités
    1.64
     każ
    1.62
     évo
    1.62
    Activations Density 0.007%

    No Known Activations