© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11379
    Prev
    Next
    INDEX
    Explanations

    gender roles and stereotypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     desorption
    0.45
    cretion
    0.40
     도시
    0.40
    ोंग
    0.39
     標準
    0.39
    🥫
    0.39
     Markov
    0.38
     trúc
    0.38
     possession
    0.37
    ("+
    0.37
    POSITIVE LOGITS
     women
    1.52
     gender
    1.51
    Gender
    1.51
     Women
    1.48
    Women
    1.48
     female
    1.46
     женщин
    1.46
    女性
    1.45
     여성
    1.43
     Gender
    1.42
    Activations Density 0.316%

    No Known Activations