© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13897
    Prev
    Next
    INDEX
    Explanations

    LGBTQ+ terms and identities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    酸素
    0.88
     deterioration
    0.84
     erosion
    0.82
    CCl
    0.82
     XPath
    0.82
     deterior
    0.79
     raster
    0.79
    悬
    0.78
     underestimate
    0.77
     debris
    0.77
    POSITIVE LOGITS
     transgender
    1.95
     LGBTQ
    1.91
    LGBT
    1.89
     LGBT
    1.83
     lesbian
    1.82
     homosexuality
    1.65
     homosexual
    1.60
     Lesbian
    1.51
     Queer
    1.51
    🏳
    1.49
    Activations Density 0.461%

    No Known Activations