© 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. 117086
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     sogen
    -0.07
     যাঁ
    -0.06
    ঘ্র
    -0.06
    八
    -0.06
    七
    -0.06
    牴
    -0.06
    Such
    -0.06
    Would
    -0.06
    而在
    -0.06
    。(
    -0.06
    POSITIVE LOGITS
     старо
    0.06
     хоть
    0.06
    hot
    0.06
     cả
    0.06
     defined
    0.06
     менен
    0.06
     combination
    0.06
    ǰ
    0.05
     Something
    0.05
     plagued
    0.05
    Activations Density 0.000%

    No Known Activations