© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81767
    Prev
    Next
    INDEX
    Explanations

    transgender and gender topics

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

    gender and transgender identities and pronouns

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     oblique
    0.44
    markets
    0.43
     斜
    0.41
    だけに
    0.41
    barrow
    0.41
     obliqu
    0.40
    斜
    0.40
     ባለ
    0.39
     부동산
    0.39
    饕
    0.39
    POSITIVE LOGITS
     transgender
    1.27
     gender
    1.01
     Gender
    0.97
    gender
    0.95
    Gender
    0.93
     ट्रांसजेंडर
    0.88
     genders
    0.84
     transg
    0.84
     LGBTQ
    0.84
     dysph
    0.80
    Activations Density 0.040%

    No Known Activations