© 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. 115975
    Prev
    Next
    INDEX
    Explanations

    andorwhat is

    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
     в
    -0.06
    ・
    -0.06
    分割
    -0.06
     другим
    -0.06
     externes
    -0.06
     อีก
    -0.06
     melhorar
    -0.06
     tentativa
    -0.06
    然后再
    -0.06
    みたいな
    -0.06
    POSITIVE LOGITS
     went
    0.07
     বিভিন্ন
    0.07
     ملاحظ
    0.07
     गर्लफ्रेंड
    0.06
     If
    0.06
    精灵
    0.06
     Shelley
    0.06
    來到
    0.06
     homeowners
    0.06
    ambio
    0.06
    Activations Density 0.030%

    No Known Activations