© 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. 10-GEMMASCOPE-RES-131K
    7. 41340
    Prev
    Next
    INDEX
    Explanations

    Chinese

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

    The neuron selectively activates on tokens containing the character sequence “chin,” i.e. references to China/Chinese.

    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
    ’
    -2.61
     have
    -1.97
    This
    -1.95
     таке
    -1.80
     believes
    -1.76
     Two
    -1.74
     encompasses
    -1.73
     “[
    -1.73
     unquestionably
    -1.72
     について
    -1.68
    POSITIVE LOGITS
    </h5>
    2.03
    in
    1.94
    你还
    1.86
     were
    1.84
    豨
    1.77
     towns
    1.73
    wonderful
    1.68
    锒
    1.67
    鞮
    1.63
     interessante
    1.63
    Activations Density 0.017%

    No Known Activations