© 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. 127931
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
     substantial
    -0.06
     çalış
    -0.06
     любую
    -0.06
    )
    -0.06
     ওদের
    -0.06
     ounce
    -0.06
     up
    -0.06
     Counts
    -0.06
    Ꮯ
    -0.06
     तत्व
    -0.06
    POSITIVE LOGITS
    America
    0.06
     also
    0.06
     म्यु
    0.06
    सो
    0.06
    遺伝
    0.06
     indeed
    0.06
    might
    0.06
    Shelf
    0.06
     America
    0.06
     funcionario
    0.06
    Activations Density 0.001%

    No Known Activations