© 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. 121009
    Prev
    Next
    INDEX
    Explanations

    combining or both

    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
     других
    -0.07
     różnych
    -0.07
     drugih
    -0.07
     stvarn
    -0.07
     разных
    -0.06
     drugiej
    -0.06
     supplementing
    -0.06
     व्यापक
    -0.06
     různých
    -0.06
     způ
    -0.06
    POSITIVE LOGITS
     aby
    0.06
    四大
    0.06
     PSD
    0.06
     সেনাদের
    0.06
    を受ける
    0.05
     হয়
    0.05
     denoted
    0.05
    シャー
    0.05
     Christi
    0.05
     deteriorate
    0.05
    Activations Density 0.041%

    No Known Activations