© 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. 121070
    Prev
    Next
    INDEX
    Explanations

    compared, superior, preferable

    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
     test
    -0.06
    immediately
    -0.06
     Eighty
    -0.06
    enabled
    -0.06
     проводи
    -0.06
     здійсню
    -0.06
     осуществляется
    -0.06
     تفسیر
    -0.06
     tests
    -0.06
     Eight
    -0.06
    POSITIVE LOGITS
    比如
    0.07
     compared
    0.07
    比べて
    0.07
     শ্রেষ্ঠ
    0.06
     preferred
    0.06
     superior
    0.06
     preferable
    0.06
     superiority
    0.06
     preferably
    0.06
     दोघा
    0.06
    Activations Density 0.030%

    No Known Activations