© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48854
    Prev
    Next
    INDEX
    Explanations

    attractive men and physical build

    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_65k_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
     heroine
    0.70
     actresses
    0.66
    👸
    0.64
     कुमारी
    0.62
     लक्ष्मीबाई
    0.62
     progesterone
    0.61
     హీరోయి
    0.60
    妳
    0.60
     বেগম
    0.58
     कन्या
    0.58
    POSITIVE LOGITS
     handsome
    0.95
    handsome
    0.80
     shirtless
    0.80
     Handsome
    0.77
     সুদর্শন
    0.75
    帥
    0.69
    Handsome
    0.69
    帅
    0.69
     frontman
    0.66
     himself
    0.61
    Activations Density 0.057%

    No Known Activations