© 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. 34-GEMMASCOPE-RES-131K
    7. 91591
    Prev
    Next
    INDEX
    Explanations

    women in education and science

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

    organization names that include phrases like "Women in" or "Women for" followed by a field or purpose.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    eneral
    -0.90
    taient
    -0.88
     zéro
    -0.87
     bouteilles
    -0.86
     châssis
    -0.85
     duradero
    -0.82
     pourront
    -0.80
     خواهند
    -0.80
    ⡷
    -0.79
    HideFlags
    -0.79
    POSITIVE LOGITS
     Science
    0.96
     science
    0.88
     cytometry
    0.84
     if
    0.82
     that
    0.81
    графії
    0.78
     Medicaid
    0.78
     it
    0.78
     s
    0.77
     Profile
    0.76
    Activations Density 0.038%

    No Known Activations