© 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. 34-GEMMASCOPE-RES-131K
    7. 106256
    Prev
    Next
    INDEX
    Explanations

    "White" followed by common nouns

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

    The neuron detects occurrences of the word “white” (including hyphenated forms and various capitalizations).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ausser
    -0.89
    acağ
    -0.88
     likewise
    -0.85
    の前に
    -0.84
    のではないか
    -0.84
     additionally
    -0.83
     Stratton
    -0.82
     Pras
    -0.79
    法师
    -0.79
    ,’
    -0.78
    POSITIVE LOGITS
    White
    1.57
     White
    1.55
     white
    1.52
    white
    1.49
     白
    1.43
    washed
    1.38
    WHITE
    1.38
     ホワイト
    1.35
    的白
    1.34
    wash
    1.30
    Activations Density 0.037%

    No Known Activations