© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116078
    Prev
    Next
    INDEX
    Explanations

    font data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    三个
    -0.06
     প্রস্তুত
    -0.06
     artific
    -0.06
     Encore
    -0.06
     antagon
    -0.06
     unsatisfactory
    -0.06
     इनो
    -0.06
     overnight
    -0.06
    zień
    -0.06
    最佳
    -0.06
    POSITIVE LOGITS
     some
    0.06
     letras
    0.06
    ที่เป็น
    0.06
     verwendet
    0.06
     माइक
    0.06
     childish
    0.06
     benutzt
    0.06
     einige
    0.06
     verstehen
    0.05
     dado
    0.05
    Activations Density 0.003%

    No Known Activations