© 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. 128533
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units like minutes or words like 'or'

    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
     -
    -0.07
    ww
    -0.06
    <0x10>
    -0.06
    /
    -0.06
    เรียน
    -0.05
     क्षेत्रा
    -0.05
     zweite
    -0.05
     khuyến
    -0.05
    wwww
    -0.05
     மற்ற
    -0.05
    POSITIVE LOGITS
     in
    0.09
     glorious
    0.07
     không
    0.07
     रूप
    0.07
     creating
    0.07
     সবাই
    0.07
     crucial
    0.06
     fabulous
    0.06
     не
    0.06
     rio
    0.06
    Activations Density 0.006%

    No Known Activations