© 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. 103851
    Prev
    Next
    INDEX
    Explanations

    Saudi Arabia and Gulf politics

    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
     tucked
    -0.77
     culturas
    -0.73
     captures
    -0.73
    osomal
    -0.72
     Bescheid
    -0.71
    wanza
    -0.71
     tecnica
    -0.70
     categories
    -0.69
     feliz
    -0.68
     socialista
    -0.68
    POSITIVE LOGITS
     Saudi
    1.38
    Saudi
    1.33
     Bahrain
    1.08
     GCC
    1.04
     Riyadh
    1.03
     Sunni
    1.02
     Gulf
    1.02
     Crown
    0.98
     Qatar
    0.97
    upported
    0.96
    Activations Density 0.027%

    No Known Activations