© 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. 116491
    Prev
    Next
    INDEX
    Explanations

    Mitchel, Nyhavn, Q: invention

    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
     perubahan
    -0.06
     важ
    -0.06
     રાખો
    -0.06
     olan
    -0.06
     আট
    -0.06
     اقدامات
    -0.06
     areas
    -0.06
     Popul
    -0.06
     examinations
    -0.05
    的重要
    -0.05
    POSITIVE LOGITS
     biznes
    0.07
    fireplace
    0.06
     watertight
    0.06
     जेव्हा
    0.06
    Eventually
    0.06
    Defined
    0.06
     поскольку
    0.06
    usiness
    0.06
     toddler
    0.06
     જ્યારે
    0.06
    Activations Density 0.001%

    No Known Activations