© 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. 120906
    Prev
    Next
    INDEX
    Explanations

    android app sdk

    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
    MAX
    -0.06
    TreeView
    -0.06
     پہا
    -0.06
     sanction
    -0.06
    getTotal
    -0.06
     divisive
    -0.05
    樹
    -0.05
     감독
    -0.05
     calculating
    -0.05
     Cider
    -0.05
    POSITIVE LOGITS
    🕯
    0.07
    ంటి
    0.07
     одной
    0.06
     Other
    0.06
     безопасность
    0.06
    蹼
    0.06
    friendly
    0.06
     หนึ่ง
    0.06
     одним
    0.06
     coworker
    0.06
    Activations Density 0.006%

    No Known Activations