© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119782
    Prev
    Next
    INDEX
    Explanations

    metabolism and its disorders/diseases

    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
     uses
    -0.07
     use
    -0.06
    开发
    -0.06
    利用
    -0.06
    
    -0.06
     μέσω
    -0.06
     факти
    -0.06
     equivalents
    -0.06
     knuckles
    -0.06
    開發
    -0.06
    POSITIVE LOGITS
     ஏதாவது
    0.08
    之类的
    0.06
     esteemed
    0.06
    ต่างๆ
    0.06
     veritable
    0.06
     storied
    0.06
     disparate
    0.06
     trustworthy
    0.06
     venerable
    0.06
    嚟
    0.06
    Activations Density 0.018%

    No Known Activations