© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8844
    Prev
    Next
    INDEX
    Explanations

    men's clothing and grooming

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

    masculinity and male attributes

    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_40_width_16k_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
     heroine
    1.05
     actresses
    1.02
     करेंगी
    1.00
     অভিনেত্র
    0.99
    👸
    0.99
     herself
    0.98
     Actress
    0.96
     ছাত্রী
    0.96
    女優
    0.94
     অভিনেত্রী
    0.93
    POSITIVE LOGITS
     manly
    1.70
     masculinity
    1.55
     manhood
    1.54
     Mascul
    1.34
     gentlemen
    1.29
     macho
    1.29
     fathers
    1.28
     masculine
    1.28
     boyhood
    1.27
    紳
    1.25
    Activations Density 0.677%

    No Known Activations