© 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. 117705
    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
     generalmente
    -0.08
    Session
    -0.07
     generally
    -0.07
    generally
    -0.07
     généralement
    -0.07
     geralmente
    -0.07
    一般
    -0.07
    Generally
    -0.06
    واصل
    -0.06
     meeste
    -0.06
    POSITIVE LOGITS
     마음
    0.07
     처음
    0.07
     এবং
    0.07
    ifiez
    0.06
     và
    0.06
    していて
    0.06
     মনের
    0.06
     trakcie
    0.06
    DropDownItems
    0.06
     يتح
    0.06
    Activations Density 0.000%

    No Known Activations