© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9448
    Prev
    Next
    INDEX
    Explanations

    gender and sexual identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     herd
    1.40
     yield
    1.32
     plow
    1.29
    zos
    1.29
    пу
    1.27
    熟
    1.25
    ழு
    1.21
    (".//
    1.20
    ma
    1.20
    сора
    1.20
    POSITIVE LOGITS
     lesbian
    1.91
     transgender
    1.90
     LGBT
    1.84
     homosexual
    1.70
     bisexual
    1.68
     Lesbian
    1.68
     gays
    1.66
     homophobic
    1.58
     LGBTQ
    1.57
     gay
    1.53
    Activations Density 0.198%

    No Known Activations