© 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. 120817
    Prev
    Next
    INDEX
    Explanations

    import random, websites, Facebook

    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
     will
    -0.06
    ');
    -0.06
     is
    -0.06
     are
    -0.06
    )];
    -0.06
     or
    -0.06
    uminescent
    -0.05
     النه
    -0.05
     частично
    -0.05
     ismi
    -0.05
    POSITIVE LOGITS
     这个
    0.07
    與
    0.07
     because
    0.07
    This
    0.07
     expanse
    0.07
    According
    0.07
     ఇప్పుడు
    0.07
     socioeconomic
    0.06
     mainstay
    0.06
     因为
    0.06
    Activations Density 0.001%

    No Known Activations