© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6831
    Prev
    Next
    INDEX
    Explanations

    female names and titles

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

    female first names

    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_53_width_65k_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
     ছাত্রদের
    0.73
    男子
    0.71
    男生
    0.71
     чолові
    0.70
     mężczy
    0.70
    👬
    0.69
     pria
    0.69
     парни
    0.68
    👨
    0.68
     hombres
    0.67
    POSITIVE LOGITS
     Elizabeth
    1.58
     Elisabeth
    1.58
     Agnes
    1.55
     Margaret
    1.53
     Louise
    1.53
     Sophie
    1.52
     Dorothy
    1.52
     Irene
    1.52
     Rebecca
    1.51
     Edith
    1.49
    Activations Density 0.564%

    No Known Activations