© 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. 28354
    Prev
    Next
    INDEX
    Explanations

    feminism, gender, and women

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

    The neuron detects mentions of feminism or feminist‐related concepts (e.g. “feminist,” “intersectional feminism,” key feminist names/topics).

    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
     from
    -1.25
    hlás
    -1.08
    );
    -0.99
    هة
    -0.97
    ꧂
    -0.95
    ائه
    -0.95
    侃
    -0.94
     dramatique
    -0.94
    𝚎
    -0.93
     melap
    -0.92
    POSITIVE LOGITS
     women
    2.41
     Women
    2.14
    Women
    2.11
    women
    1.94
     WOMEN
    1.80
     womens
    1.70
     γυναι
    1.59
     woman
    1.56
     ladies
    1.51
     Womens
    1.48
    Activations Density 0.181%

    No Known Activations