© 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. 117618
    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
     slightly
    -0.06
     všetky
    -0.06
     Incorrect
    -0.06
     Slightly
    -0.06
    也就是说
    -0.06
    ,
    -0.06
    সমস্ত
    -0.06
     unauthorized
    -0.06
    অর্থাৎ
    -0.06
     associated
    -0.05
    POSITIVE LOGITS
     of
    0.06
     yang
    0.06
     which
    0.06
    ábban
    0.06
     которая
    0.06
    negara
    0.06
     meminta
    0.06
    рода
    0.06
    Brexit
    0.06
     którą
    0.06
    Activations Density 0.000%

    No Known Activations