© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3372
    Prev
    Next
    INDEX
    Explanations

    Navajo Nation

    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
     tect
    -0.81
    ੧
    -0.78
    મ
    -0.75
    getBounds
    -0.73
     Sola
    -0.71
     cata
    -0.71
    矛
    -0.70
    acate
    -0.70
     temperate
    -0.69
     قطر
    -0.69
    POSITIVE LOGITS
    Arizona
    1.18
     Arizona
    1.18
     Navajo
    1.13
     Din
    0.80
    ungguhnya
    0.80
     Chapters
    0.78
     Ariz
    0.77
     Ath
    0.77
     tł
    0.77
    Zah
    0.76
    Activations Density 0.051%

    No Known Activations