© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38464
    Prev
    Next
    INDEX
    Explanations

    technical terms and their context

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

    The neuron activates on Chinese-character tokens (i.e. words written in Chinese) within the mixed-language document.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ского
    -2.20
     RSITY
    -2.14
    縐
    -2.13
    ynthesis
    -2.09
     this
    -2.05
    ୌ
    -2.03
     methode
    -2.02
    
    -2.02
    墬
    -1.99
    żyć
    -1.98
    POSITIVE LOGITS
     zehn
    2.02
     THEIR
    1.99
    筇
    1.91
     tzw
    1.90
     ggf
    1.87
     Jika
    1.87
     generó
    1.84
    尤其是
    1.84
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.80
     ewig
    1.80
    Activations Density 0.017%

    No Known Activations