© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59582
    Prev
    Next
    INDEX
    Explanations

    female kinship and roles

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

    feminine identity and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Obrigado
    0.70
     manhood
    0.66
     boyhood
    0.65
     thằng
    0.65
    ‍♂️
    0.61
     himself
    0.60
     remaster
    0.57
    youtu
    0.57
     brotherhood
    0.56
     frontman
    0.55
    POSITIVE LOGITS
     엄마
    0.97
     maternity
    0.89
    👭
    0.89
     actresses
    0.86
     cantik
    0.85
     mamá
    0.84
     niñas
    0.84
     embarazada
    0.84
     policewomen
    0.83
    姐妹
    0.82
    Activations Density 0.091%

    No Known Activations