© 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. 120836
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
     atrocious
    -0.07
     '<%=
    -0.06
     numerous
    -0.06
     innumerable
    -0.06
     egregious
    -0.06
     așa
    -0.06
    \{{}\
    -0.06
     многочис
    -0.06
    Пра
    -0.06
    В
    -0.06
    POSITIVE LOGITS
     व
    0.07
     ใน
    0.07
     هم
    0.06
     पनि
    0.06
    urope
    0.06
     বাহাদুর
    0.06
    HomeScreen
    0.06
     במ
    0.06
     দেওয়ার
    0.06
     ਅਤੇ
    0.06
    Activations Density 0.001%

    No Known Activations