© 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. 98677
    Prev
    Next
    INDEX
    Explanations

    African languages and South African locations

    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
     Ministry
    -0.75
    pll
    -0.75
    pler
    -0.70
     menyambut
    -0.70
    Amit
    -0.69
    utscher
    -0.69
    ijer
    -0.68
    glTexCoord
    -0.68
    硝
    -0.67
    Ministry
    -0.67
    POSITIVE LOGITS
    Venda
    1.10
    zwi
    0.74
    吸収
    0.73
    expects
    0.71
    hobia
    0.70
    ḓ
    0.69
     счета
    0.68
    Vh
    0.68
    brian
    0.68
    .+\
    0.67
    Activations Density 0.017%

    No Known Activations