© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 18011
    Prev
    Next
    INDEX
    Explanations

    sexual matters

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

    sexualization and objectification

    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
     эффект
    0.43
    鲔
    0.40
    ጠና
    0.40
    Shares
    0.39
    Subscriptions
    0.39
    鹹
    0.39
    лер
    0.39
    Sexy
    0.38
    whitespace
    0.38
    핑
    0.38
    POSITIVE LOGITS
    uality
    0.75
    ually
    0.67
     orientation
    0.64
     harassment
    0.63
     intercourse
    0.63
     dysfunction
    0.62
     dim
    0.59
    ual
    0.59
     minorities
    0.55
     abuse
    0.55
    Activations Density 0.010%

    No Known Activations