© 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. 22-GEMMASCOPE-RES-131K
    7. 130664
    Prev
    Next
    INDEX
    Explanations

    The neuron activates strongly on words naming people’s occupations or professional titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    women in professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     его
    -1.41
     jego
    -1.38
     himself
    -1.32
     his
    -1.26
     seiner
    -1.19
    Его
    -1.15
    他的
    -1.02
    His
    -1.00
    的他
    -0.98
    rigado
    -0.95
    POSITIVE LOGITS
     women
    2.09
     female
    1.98
     she
    1.86
     herself
    1.84
    Women
    1.81
     Women
    1.80
    women
    1.77
    female
    1.75
     her
    1.73
     Female
    1.68
    Activations Density 0.087%

    No Known Activations