© 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. 22-GEMMASCOPE-RES-131K
    7. 84030
    Prev
    Next
    INDEX
    Explanations

    gender, socialization, justice

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

    The neuron specializes in detecting occurrences of the word “gender” (and closely related gender-themed terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    -2.67
    s
    -2.48
     Also
    -2.44
     kteří
    -2.41
     Of
    -2.25
     This
    -2.25
    灃
    -2.22
    '
    -2.20
    癀
    -2.17
     o
    -2.16
    POSITIVE LOGITS
    地说道
    2.69
    6
    2.34
    0
    2.30
    2
    2.23
    ྅
    2.19
    的说道
    2.11
    ሷ
    2.06
     手绘
    2.06
    狆
    2.06
     ヶ
    2.03
    Activations Density 0.005%

    No Known Activations