© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11507
    Prev
    Next
    INDEX
    Explanations

    women's expectations and equality

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

    sexist and demeaning language regarding gender

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

    feminist

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
     شہریوں
    0.44
     অভিনেতা
    0.42
     youth
    0.42
    ertel
    0.40
    𝚢
    0.40
     മഴ
    0.39
    icl
    0.39
    🌦
    0.39
    bapt
    0.38
    炳
    0.38
    POSITIVE LOGITS
     feminist
    2.05
     feminists
    1.99
     Feminist
    1.98
     feminism
    1.89
     Women
    1.78
     Femin
    1.77
    Women
    1.75
     femin
    1.73
     женщин
    1.66
     women
    1.65
    Activations Density 0.353%

    No Known Activations