© 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. 128086
    Prev
    Next
    INDEX
    Explanations

    redistribute it and/or modify it

    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
     zároveň
    -0.06
     addictive
    -0.06
    搬
    -0.06
     och
    -0.06
     स्थानांतर
    -0.06
    митри
    -0.06
     melalui
    -0.06
     maniac
    -0.05
     unimaginable
    -0.05
     असंभव
    -0.05
    POSITIVE LOGITS
     중요
    0.07
     memoria
    0.06
     አስፈላጊ
    0.06
     يكن
    0.06
     중요하다
    0.06
    important
    0.06
     hydrothermal
    0.06
     этого
    0.06
    期待
    0.06
     ውጤ
    0.06
    Activations Density 0.003%

    No Known Activations