© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4254
    Prev
    Next
    INDEX
    Explanations

    ancient Egypt and Egyptians

    np_acts-logits-general · gemini-2.5-flash-lite

    Ancient Egyptian civilization, art, worship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ំនួន
    0.51
    韩
    0.51
    Korean
    0.50
    枫
    0.49
    锻
    0.48
    쯜
    0.46
    pacific
    0.46
    ɭ
    0.46
    Seattle
    0.46
    Seoul
    0.45
    POSITIVE LOGITS
     Egyptian
    1.70
     Egypt
    1.67
     egypt
    1.67
     egyptian
    1.56
    埃及
    1.52
    Egypt
    1.50
    Egyptian
    1.48
     Egyptians
    1.46
     egip
    1.46
     المصرية
    1.37
    Activations Density 0.055%

    No Known Activations