© 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. 128024
    Prev
    Next
    INDEX
    Explanations

    tests, video games, legal documents

    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
     nefarious
    -0.07
     হইল
    -0.06
     зовніш
    -0.06
     істори
    -0.06
     স্ক্র
    -0.06
    最新的
    -0.06
    に必要な
    -0.06
    getinfo
    -0.06
     பிற
    -0.06
    に入れ
    -0.06
    POSITIVE LOGITS
     filePath
    0.06
    peptide
    0.06
     UIImage
    0.06
    两年
    0.06
    Expressions
    0.06
    Award
    0.06
     &/
    0.06
    Application
    0.05
    Certificate
    0.05
     बर्तन
    0.05
    Activations Density 0.004%

    No Known Activations