© 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. 120426
    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
     rar
    -0.06
     has
    -0.06
     scarce
    -0.06
    minify
    -0.06
    Insider
    -0.06
    還
    -0.06
     altered
    -0.06
    调整
    -0.05
    还
    -0.05
     yet
    -0.05
    POSITIVE LOGITS
     oamen
    0.08
     on
    0.07
     সকল
    0.06
     একদম
    0.06
     zarówno
    0.06
     oni
    0.06
     äl
    0.06
     in
    0.06
     প্রত্যেক
    0.06
    getAddress
    0.06
    Activations Density 0.000%

    No Known Activations