© 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. 34-GEMMASCOPE-RES-131K
    7. 84672
    Prev
    Next
    INDEX
    Explanations

    sex and gender assigned

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

    The neuron fires on highly technical molecular‐biology and genetics terminology—especially gene names, protein factors, developmental pathways, and sex‐determination keywords.

    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
     redeem
    -0.82
    Executing
    -0.80
    Execu
    -0.78
    Executed
    -0.72
    Ecc
    -0.71
    Bienvenido
    -0.70
    Diameter
    -0.69
     Reap
    -0.68
     gửi
    -0.67
     redemption
    -0.66
    POSITIVE LOGITS
     sex
    1.55
     XY
    1.34
    assigned
    1.28
     assigned
    1.23
    ASSIGN
    1.10
    Sex
    1.09
     Assigned
    1.07
     anatomy
    1.06
    XY
    1.05
    sex
    1.04
    Activations Density 0.068%

    No Known Activations