© 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. 22-GEMMASCOPE-RES-131K
    7. 39395
    Prev
    Next
    INDEX
    Explanations

    internationalization (i18n)

    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_22/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
    ſelf
    -2.05
    gangss
    -1.87
    泐
    -1.71
    卝
    -1.59
    蛱
    -1.59
    genodigd
    -1.58
    祧
    -1.56
     armado
    -1.54
    indest
    -1.50
    formatie
    -1.46
    POSITIVE LOGITS
    *
    1.88
    1
    1.66
    5
    1.55
    4
    1.33
    子育て
    1.29
     продукт
    1.28
    wać
    1.27
    но
    1.27
     byproduct
    1.23
    in
    1.23
    Activations Density 0.003%

    No Known Activations