© 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. 116215
    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
     November
    -0.07
     menyebabkan
    -0.07
    November
    -0.07
     Jen
    -0.06
     connects
    -0.06
     December
    -0.06
     siguen
    -0.06
    touch
    -0.06
     चीजें
    -0.06
     solamente
    -0.06
    POSITIVE LOGITS
    W
    0.06
     পণ
    0.06
    భా
    0.06
     Defensive
    0.06
    Ҳ
    0.06
    Schwarz
    0.06
     eenvoudig
    0.06
     zde
    0.06
     netto
    0.06
     동물
    0.06
    Activations Density 0.000%

    No Known Activations