© 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. 121017
    Prev
    Next
    INDEX
    Explanations

    beauty / digital / adults / development / nuclear / thermal

    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
     поддержа
    -0.08
     поддержи
    -0.07
    常に
    -0.07
     potencialmente
    -0.07
     weekend
    -0.07
     поддерживает
    -0.07
     sürekli
    -0.07
     semanal
    -0.07
     ежедневно
    -0.06
    晚上
    -0.06
    POSITIVE LOGITS
    卻
    0.07
    却
    0.07
     ἢ
    0.07
     before
    0.07
     모습
    0.06
    ō
    0.06
     your
    0.06
    又は
    0.06
     allerdings
    0.06
    ก่อน
    0.06
    Activations Density 0.003%

    No Known Activations