© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116541
    Prev
    Next
    INDEX
    Explanations

    sexual identity and related fields

    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
     crops
    -0.79
     HIV
    -0.79
    ajan
    -0.78
     transgender
    -0.77
     ethnic
    -0.75
     Muslim
    -0.75
     pixels
    -0.73
     vaping
    -0.73
     racism
    -0.73
     Gender
    -0.73
    POSITIVE LOGITS
     invert
    0.82
    medico
    0.81
    र्स
    0.80
     psychiatrists
    0.80
     Uran
    0.80
    Sneaky
    0.76
    tactos
    0.76
     congrès
    0.75
    Uran
    0.74
     Excerpt
    0.74
    Activations Density 0.031%

    No Known Activations