© 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. 127913
    Prev
    Next
    INDEX
    Explanations

    code syntax and indentation

    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
     reacción
    -0.06
    aggregated
    -0.06
    ሰራ
    -0.05
    chievement
    -0.05
    ষ্কৃত
    -0.05
     showc
    -0.05
    ✂
    -0.05
    ികള
    -0.05
    reason
    -0.05
    如果是
    -0.05
    POSITIVE LOGITS
     eine
    0.06
     जिसे
    0.06
     તેણે
    0.06
     【
    0.06
     mūsų
    0.06
     an
    0.06
    保证金
    0.06
    ilizce
    0.06
     berjudul
    0.06
     Sachen
    0.06
    Activations Density 0.001%

    No Known Activations