© 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. 141614
    Prev
    Next
    INDEX
    Explanations

    women's traits and expectations

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

    women's promotion, celebration, and admission

    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
     धातु
    0.53
     психи
    0.46
     REACTORS
    0.44
     টাই
    0.43
     rezat
    0.43
     ==>
    0.43
     ebb
    0.42
    <unused1018>
    0.42
     була
    0.42
     мета
    0.42
    POSITIVE LOGITS
    promotion
    0.53
    women
    0.51
    ewek
    0.49
     celebration
    0.47
    omme
    0.47
    ess
    0.46
     femmes
    0.46
    ometric
    0.45
    Women
    0.45
     women
    0.45
    Activations Density 0.001%

    No Known Activations