© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83718
    Prev
    Next
    INDEX
    Explanations

    sex and gender

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

    This neuron detects numeric tokens (numbers and digit sequences).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    anting
    -0.78
     POINTS
    -0.77
     woman
    -0.76
     comarca
    -0.76
     holdings
    -0.76
     oscura
    -0.75
     Girlfriend
    -0.73
    female
    -0.73
     schlug
    -0.72
    male
    -0.70
    POSITIVE LOGITS
     opposite
    1.80
     sexes
    1.48
    opposite
    1.42
     sex
    1.41
     fairer
    1.38
    Opposite
    1.37
     Opposite
    1.32
     genders
    1.20
     Sex
    1.09
     gender
    1.05
    Activations Density 0.033%

    No Known Activations