© 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. 6672
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and foreign words

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

    The neuron fires strongly on tokens containing non-English letters or diacritics (e.g. accented or macronized characters).

    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
     was
    -2.20
     Despite
    -2.09
     achieving
    -1.98
     attaining
    -1.92
     achieved
    -1.91
    0
    -1.91
     Though
    -1.89
     provides
    -1.88
     forming
    -1.86
     enables
    -1.83
    POSITIVE LOGITS
    of
    2.09
     realmente
    1.98
    憷
    1.87
    毟
    1.84
     donné
    1.77
    🧌
    1.77
    
    1.77
     !!!!
    1.77
     they
    1.76
     např
    1.76
    Activations Density 0.047%

    No Known Activations