© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101282
    Prev
    Next
    INDEX
    Explanations

    gender roles & equity

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

    This neuron activates on the word “gender” (and its variants) wherever it appears.

    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
    籥
    -3.09
     kteří
    -2.67
    '
    -2.55
    癀
    -2.55
    y
    -2.45
    ⩴
    -2.42
     Also
    -2.36
    盌
    -2.34
    轳
    -2.33
    s
    -2.31
    POSITIVE LOGITS
    地说道
    3.25
    6
    3.08
    0
    2.95
    3
    2.95
    2
    2.89
    的说道
    2.66
    狆
    2.44
    9
    2.39
    5
    2.38
    地说
    2.34
    Activations Density 0.006%

    No Known Activations