© 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. 120871
    Prev
    Next
    INDEX
    Explanations

    qualified writer

    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
     কার্যকরী
    -0.06
    を指定
    -0.06
     nonostante
    -0.06
     Fuck
    -0.06
    แม้
    -0.06
    THANK
    -0.06
     contributions
    -0.06
     Несмотря
    -0.06
     जुलाई
    -0.06
     오랜
    -0.06
    POSITIVE LOGITS
     সংক্রম
    0.06
     ayrıca
    0.06
     одоб
    0.05
     seaport
    0.05
     दिखाते
    0.05
     राजवंश
    0.05
    ె
    0.05
     المبار
    0.05
    sru
    0.05
    oly
    0.05
    Activations Density 0.005%

    No Known Activations