© 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. 1794
    Prev
    Next
    INDEX
    Explanations

    Celtic or Slavic traditions

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

    The neuron activates whenever it sees any form of the string “Celt” (e.g. Celtic, Celts, Celtics).

    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
    過的
    -2.72
    蹓
    -2.61
     夜景
    -2.59
    居る
    -2.59
    還沒
    -2.34
     ACTUALLY
    -2.27
    最初から
    -2.27
    
    -2.23
    讓他
    -2.22
    這麼
    -2.20
    POSITIVE LOGITS
    ized
    2.41
    新
    2.23
    ’
    2.19
    ;
    2.14
     well
    2.09
     untuk
    2.08
    to
    2.06
     để
    2.03
    tidos
    2.00
     начинают
    1.95
    Activations Density 0.002%

    No Known Activations