© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124288
    Prev
    Next
    INDEX
    Explanations

    personal information concerning individuals

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

    biological sex and gender

    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
    Not in Any Lists

    No Comments

    Negative Logits
     কর্মকাণ্ড
    0.40
    海洋
    0.40
     பிரமி
    0.40
     রোজ
    0.40
     коопера
    0.39
     Pemerintah
    0.39
    👪
    0.39
    葡萄酒
    0.38
    🌭
    0.38
     Governmental
    0.38
    POSITIVE LOGITS
     misog
    0.46
     biological
    0.45
    anne
    0.44
     Emma
    0.43
     ladies
    0.43
     CW
    0.41
     mae
    0.41
     athlete
    0.40
     gender
    0.40
     genitals
    0.40
    Activations Density 0.092%

    No Known Activations