© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118235
    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
     they
    -0.06
    巅
    -0.06
     array
    -0.06
     thay
    -0.06
     of
    -0.06
    退休
    -0.06
     a
    -0.05
    꿉
    -0.05
     statist
    -0.05
     at
    -0.05
    POSITIVE LOGITS
    䊀
    0.07
     dugo
    0.07
     männ
    0.06
     மீட்டர்
    0.06
     allgemeinen
    0.06
     bislang
    0.06
     ранее
    0.06
     både
    0.06
     요구
    0.06
    䘚
    0.06
    Activations Density 0.000%

    No Known Activations