© 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. 34-GEMMASCOPE-RES-131K
    7. 77955
    Prev
    Next
    INDEX
    Explanations

    women and girls

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

    The neuron fires strongly on words that appear in titles or headings—i.e. tokens in title‐case or all‐caps formatting.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     frontman
    -1.27
    ‍♂️
    -1.27
     Grandpa
    -1.20
     çocu
    -1.12
     พ่อ
    -1.12
    พ่อ
    -1.09
     parenthood
    -1.09
     masculinity
    -1.06
     grandpa
    -1.05
    👨
    -1.05
    POSITIVE LOGITS
     women
    3.84
     girls
    3.77
     ladies
    3.39
    girls
    2.88
    women
    2.84
    Girls
    2.64
     sisters
    2.59
     girl
    2.55
    Women
    2.55
     Girls
    2.48
    Activations Density 0.256%

    No Known Activations