© 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. 10-GEMMASCOPE-RES-131K
    7. 119616
    Prev
    Next
    INDEX
    Explanations

    IMMIGRATION and specific names

    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_10/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
    a
    -2.72
    -2.61
     {
    -2.59
    s
    -2.53
     “
    -2.50
     изменений
    -2.47
    ing
    -2.45
    羮
    -2.39
    pulseira
    -2.30
    主要是
    -2.27
    POSITIVE LOGITS
    AutoresizingMask
    2.91
     یا
    2.36
    where
    2.34
    ."
    2.34
    (
    2.33
    𝐲
    2.33
     și
    2.31
    颙
    2.31
    瑧
    2.28
    🥶
    2.25
    Activations Density 0.003%

    No Known Activations