© 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. 38375
    Prev
    Next
    INDEX
    Explanations

    LGBTQ and Pratt

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

    This neuron activates on uppercase tokens—especially acronyms and other all-caps or title-case words (e.g. “LGBTQ,” “Natl,” “Pratt”).

    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
    A
    -3.39
     -
    -3.08
    They
    -3.03
     Primarily
    -2.98
     Mainly
    -2.83
    The
    -2.81
    9
    -2.75
    r
    -2.72
     Honestly
    -2.58
    P
    -2.56
    POSITIVE LOGITS
    脔
    2.78
    而又
    2.67
    蠃
    2.66
    玙
    2.64
     leaſt
    2.56
    Ꭸ
    2.55
    teten
    2.53
    轳
    2.53
    ⢕
    2.50
    ſſen
    2.48
    Activations Density 0.001%

    No Known Activations