© 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. 118420
    Prev
    Next
    INDEX
    Explanations

    democracy and democratic systems

    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
    pausal
    -0.78
    dpi
    -0.77
    DIA
    -0.75
    ficas
    -0.74
    ppert
    -0.74
    detail
    -0.71
    ड़ा
    -0.69
     pimiento
    -0.68
    ícia
    -0.68
    न्ध
    -0.68
    POSITIVE LOGITS
     democracy
    5.09
    democracy
    3.78
     Democracy
    3.72
    Democracy
    3.48
     democracia
    3.27
     democracies
    3.02
     democratic
    3.02
     демокра
    2.98
     demokra
    2.72
     démocratie
    2.67
    Activations Density 0.037%

    No Known Activations