© 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. 117238
    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
     it
    -0.07
     but
    -0.06
     Ä
    -0.06
     이렇게
    -0.06
    долго
    -0.06
    Certain
    -0.06
     as
    -0.05
     a
    -0.05
    plicit
    -0.05
    이렇게
    -0.05
    POSITIVE LOGITS
     Hundred
    0.06
     مركز
    0.06
     oferecer
    0.06
     Main
    0.06
     Vương
    0.06
    ђ
    0.06
     wyróż
    0.06
     center
    0.06
    รั่ง
    0.06
     ofrecer
    0.06
    Activations Density 0.000%

    No Known Activations