© 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. 119199
    Prev
    Next
    INDEX
    Explanations

    abortion laws and providers

    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
     infant
    -0.90
     newborn
    -0.78
     jurors
    -0.78
     Analytic
    -0.75
    Lake
    -0.75
     prenatal
    -0.73
    slideUp
    -0.71
     erratic
    -0.71
     biologique
    -0.71
    unken
    -0.70
    POSITIVE LOGITS
     Provider
    1.02
     provider
    1.02
     providers
    1.00
     Providers
    0.85
    PROVIDER
    0.81
    Providers
    0.79
    provider
    0.77
    providers
    0.77
    Provider
    0.75
     svolge
    0.69
    Activations Density 0.036%

    No Known Activations