© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58407
    Prev
    Next
    INDEX
    Explanations

    women and their roles

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

    The neuron fires strongly on occurrences of the word “women,” especially in contexts giving counts or statistics about women.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     of
    -1.24
    だけでなく
    -1.23
     documentaire
    -1.22
    だけではなく
    -1.13
     櫃
    -1.13
     polícia
    -1.12
     Añ
    -1.11
    攆
    -1.09
     churras
    -1.09
    cuerdo
    -1.09
    POSITIVE LOGITS
     (!)
    1.40
     “
    1.35
     deseas
    1.32
     hubieran
    1.23
     kannst
    1.23
     puedan
    1.13
    (!)
    1.13
    }$.\\
    1.09
     ‘‘
    1.09
    ，“
    1.09
    Activations Density 0.092%

    No Known Activations