© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15367
    Prev
    Next
    INDEX
    Explanations

    women and brides

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     HOMO
    0.62
     homophobic
    0.61
    ǝ
    0.61
     lesbian
    0.59
     gay
    0.58
     bisexual
    0.57
     fracking
    0.57
     antihist
    0.56
     unisex
    0.55
    🕒
    0.54
    POSITIVE LOGITS
     brides
    1.67
     bride
    1.63
     mail
    1.61
     Bride
    1.48
    bride
    1.45
     Brides
    1.45
    mail
    1.40
     Mail
    1.40
    Mail
    1.38
    Bride
    1.34
    Activations Density 0.015%

    No Known Activations