© 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. 119982
    Prev
    Next
    INDEX
    Explanations

    originated by or made in

    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
     destinations
    -0.07
    ರುವುದು
    -0.06
     Allowing
    -0.06
    ☑
    -0.06
    jai
    -0.06
     destination
    -0.06
     Pary
    -0.06
     opération
    -0.06
     faster
    -0.06
     раньше
    -0.06
    POSITIVE LOGITS
    で作
    0.06
     замены
    0.06
    创造
    0.06
     inspiration
    0.06
     انتظار
    0.06
     சுகாதார
    0.06
     web
    0.06
     संयोग
    0.06
     মামলা
    0.06
     scouting
    0.06
    Activations Density 0.096%

    No Known Activations