© 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. 19696
    Prev
    Next
    INDEX
    Explanations

    Goodbye Argentina

    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
    遊んで
    -1.43
     drau
    -1.36
    遊ぶ
    -1.34
     psychi
    -1.29
    ことはありません
    -1.29
    複数
    -1.28
     错误
    -1.26
    居る
    -1.25
     manifeste
    -1.24
    liato
    -1.23
    POSITIVE LOGITS
     or
    2.48
     [
    1.59
     as
    1.59
     those
    1.48
     maybe
    1.45
     Maybe
    1.37
     perhaps
    1.34
     Perhaps
    1.33
     what
    1.31
     three
    1.31
    Activations Density 0.002%

    No Known Activations