© 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. 120942
    Prev
    Next
    INDEX
    Explanations

    Chinese government and economic terms

    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
    ভক্ত
    -0.07
    賏
    -0.06
     사용자
    -0.06
     mishaps
    -0.06
    放棄
    -0.06
     calyce
    -0.06
     škola
    -0.06
     श्रा
    -0.06
    这些
    -0.06
     preceding
    -0.06
    POSITIVE LOGITS
     cuando
    0.06
     bahwa
    0.06
     כאשר
    0.06
    ﻳ
    0.06
     Pharma
    0.06
     lorsque
    0.06
     chez
    0.06
     ke
    0.06
     cara
    0.06
     khi
    0.06
    Activations Density 0.024%

    No Known Activations