© 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. 10-GEMMASCOPE-RES-131K
    7. 42067
    Prev
    Next
    INDEX
    Explanations

    women, females, solo, occupancy

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

    This neuron is primarily activated by references to women and girls, often in discussions of their social status, rights, demographics, or vulnerabilities.

    oai_token-act-pair · gemini-2.5-flashTriggered by @loveandspam
    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
    Not in Any Lists

    No Comments

    Negative Logits
     about
    -1.44
     tava
    -1.13
     everything
    -1.06
     padang
    -1.05
     maybe
    -1.05
     usai
    -1.05
     augusti
    -1.04
    閨
    -1.04
    انى
    -1.03
     haba
    -1.02
    POSITIVE LOGITS
     byly
    1.28
     vstup
    1.21
     efekty
    1.20
     використання
    1.20
     section
    1.17
     pracuje
    1.16
     konkuren
    1.15
    itif
    1.13
     inspiración
    1.13
    adaan
    1.13
    Activations Density 0.026%

    No Known Activations