© 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. 128000
    Prev
    Next
    INDEX
    Explanations

    **Code syntax and structure**

    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
     inicio
    -0.07
     برای
    -0.06
     முதலில்
    -0.06
     sickening
    -0.06
     teria
    -0.06
     inició
    -0.06
     lúc
    -0.06
     selfish
    -0.06
     this
    -0.06
     αυτή
    -0.06
    POSITIVE LOGITS
     diber
    0.06
    essentially
    0.06
     essentially
    0.06
     محد
    0.06
     완전히
    0.06
    tras
    0.06
    もあります
    0.06
     completely
    0.06
    বাধ
    0.06
    პერ
    0.05
    Activations Density 0.001%

    No Known Activations