© 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. 3532
    Prev
    Next
    INDEX
    Explanations

    female names

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

    The neuron selectively activates on capitalized female given names.

    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
     himself
    -1.01
     grandfather
    -0.93
    Anzeige
    -0.89
     boyhood
    -0.88
    kser
    -0.84
     mares
    -0.84
     tableView
    -0.83
    δος
    -0.82
    Frauen
    -0.82
    iah
    -0.78
    POSITIVE LOGITS
     herself
    1.38
     Augusta
    0.94
     сама
    0.90
     geb
    0.89
     Ann
    0.88
    >';
    0.82
     Adelaide
    0.80
    herself
    0.79
    阿姨
    0.79
     Countess
    0.77
    Activations Density 0.072%

    No Known Activations