© 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. 121039
    Prev
    Next
    INDEX
    Explanations

    numbers and durations

    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
    あとは
    -0.07
     Altogether
    -0.07
     vollständig
    -0.07
     самих
    -0.06
     considerada
    -0.06
    ebilir
    -0.06
     Dapat
    -0.06
    都不是
    -0.06
     완전히
    -0.06
     полностью
    -0.06
    POSITIVE LOGITS
     особенно
    0.08
    Especially
    0.08
     szczególnie
    0.07
     특히
    0.06
     especially
    0.06
     Especially
    0.06
     thirty
    0.06
     particularly
    0.06
     fifty
    0.06
     insbesondere
    0.06
    Activations Density 0.023%

    No Known Activations