© 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. 103043
    Prev
    Next
    INDEX
    Explanations

    Egyptian regions and conflicts

    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
    чний
    -0.86
    Trop
    -0.84
     será
    -0.82
    летний
    -0.82
     ró
    -0.78
    ële
    -0.76
    unten
    -0.73
     نرم
    -0.73
     quy
    -0.73
     Trop
    -0.72
    POSITIVE LOGITS
     Yom
    1.25
     Six
    1.16
    Egyptian
    0.97
     Sinai
    0.96
     Egyptian
    0.95
     Arab
    0.94
     Egyptians
    0.93
    Six
    0.91
    Egypt
    0.90
     Egypt
    0.90
    Activations Density 0.017%

    No Known Activations