© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128006
    Prev
    Next
    INDEX
    Explanations

    clinical epidemiology

    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
    四年
    -0.06
    三年
    -0.06
    િતા
    -0.06
    ook
    -0.06
    áneamente
    -0.06
    混合
    -0.06
    苞
    -0.06
     trophies
    -0.06
    あらゆる
    -0.06
    이렇게
    -0.06
    POSITIVE LOGITS
     its
    0.06
     niektor
    0.06
     برخی
    0.06
     некоторые
    0.06
     etc
    0.06
     current
    0.06
     some
    0.06
     nasz
    0.06
     домаћин
    0.06
    ப்பட்டுள்ளது
    0.05
    Activations Density 0.001%

    No Known Activations