© 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. 119406
    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
    /
    -0.07
     TR
    -0.06
    inc
    -0.05
    sometimes
    -0.05
     সম্প্র
    -0.05
     and
    -0.05
     Your
    -0.05
     von
    -0.05
     if
    -0.05
     your
    -0.05
    POSITIVE LOGITS
     donnent
    0.07
     avaient
    0.07
     reclamation
    0.07
     trabajar
    0.07
    อะไร
    0.06
     ใช้
    0.06
     какого
    0.06
    という
    0.06
     politiques
    0.06
     какая
    0.06
    Activations Density 0.000%

    No Known Activations