© 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. 8566
    Prev
    Next
    INDEX
    Explanations

    transgender and LGBTQ identities

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

    gender, sex, and transgender identity

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

    transgender

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    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
     भारतीयों
    0.43
     пога
    0.42
    錫
    0.41
     FOREIGN
    0.40
    計算
    0.40
    premium
    0.40
    ியோ
    0.39
    訣
    0.39
     иностран
    0.39
     Pest
    0.38
    POSITIVE LOGITS
     transgender
    2.11
     ट्रांसजेंडर
    1.63
     gender
    1.59
     Gender
    1.54
    Gender
    1.50
    gender
    1.49
     transg
    1.41
     LGBTQ
    1.34
     genders
    1.34
    LGBT
    1.34
    Activations Density 0.098%

    No Known Activations