© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63523
    Prev
    Next
    INDEX
    Explanations

    female leadership and positions

    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_34/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
     people
    -0.96
    的他
    -0.90
    benar
    -0.89
     himself
    -0.85
     pemuda
    -0.85
    Dès
    -0.84
     Mercan
    -0.82
    └──
    -0.82
    Màu
    -0.79
    Matériel
    -0.79
    POSITIVE LOGITS
     leadership
    1.59
    leadership
    1.30
     decision
    1.21
     espacios
    1.13
     positions
    1.12
     roles
    1.10
    她们
    1.06
    decision
    1.05
     equal
    1.04
     Leadership
    1.03
    Activations Density 0.038%

    No Known Activations