© 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. 116070
    Prev
    Next
    INDEX
    Explanations

    "Q" followed by "HERE"

    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
     这些
    -0.06
     Pokud
    -0.06
    Pokud
    -0.06
     mentale
    -0.06
     這
    -0.06
     évén
    -0.06
     internally
    -0.06
     Dacă
    -0.06
     Δια
    -0.06
    ⼀
    -0.06
    POSITIVE LOGITS
     রহিয়াছে
    0.07
     curious
    0.06
     unusual
    0.06
     ಹೊಂದಿದೆ
    0.06
    矩
    0.06
     abnormal
    0.06
     ketika
    0.06
     Scheduled
    0.05
     fresh
    0.05
     practices
    0.05
    Activations Density 0.001%

    No Known Activations