© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 117889
    Prev
    Next
    INDEX
    Explanations

    medical epidemiology or technical questions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    并且
    -0.07
    ตาม
    -0.07
     bardzo
    -0.07
     bunyi
    -0.07
     очень
    -0.07
    並且
    -0.07
     by
    -0.07
    とても
    -0.06
    되고
    -0.06
    真的很
    -0.06
    POSITIVE LOGITS
     外
    0.06
     多
    0.06
     হাসপাতালে
    0.06
    চ্ছেন
    0.06
     新
    0.06
    सिया
    0.05
    Be
    0.05
    |
    0.05
    をはじめ
    0.05
     உலகம்
    0.05
    Activations Density 0.001%

    No Known Activations