© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12757
    Prev
    Next
    INDEX
    Explanations

    feminist and sexy concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    伱
    0.51
     Obrigado
    0.49
    Awesome
    0.47
     rougeâtre
    0.45
    Software
    0.44
     youngster
    0.44
    Introduceti
    0.43
     Awesome
    0.42
     Overwatch
    0.42
    갑습니다
    0.42
    POSITIVE LOGITS
     feminist
    0.72
     feminists
    0.66
     sexy
    0.65
    膣
    0.64
    💋
    0.63
     darling
    0.63
     сексуа
    0.61
     सेक्सी
    0.59
     feminism
    0.56
     Chanel
    0.56
    Activations Density 0.001%

    No Known Activations