© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14742
    Prev
    Next
    INDEX
    Explanations

    female and women

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     each
    -1.03
     to
    -1.02
     clarinet
    -0.99
     太郎
    -0.97
     waistband
    -0.96
    Televis
    -0.94
    uanya
    -0.94
    fiez
    -0.93
     Secular
    -0.93
    每一
    -0.92
    POSITIVE LOGITS
     Female
    1.47
    female
    1.35
     female
    1.34
    Women
    1.33
     gender
    1.31
     Women
    1.30
     cantik
    1.18
     Materiales
    1.18
    women
    1.16
     females
    1.16
    Activations Density 0.051%

    No Known Activations