© 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. 119966
    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
    所以
    -0.06
     at
    -0.06
    更に
    -0.06
    䛛
    -0.06
    ocrine
    -0.06
     to
    -0.06
     lagi
    -0.06
     tidligere
    -0.06
     très
    -0.06
    格局
    -0.06
    POSITIVE LOGITS
     you
    0.07
    Make
    0.06
    呮
    0.06
    fledged
    0.06
     summarize
    0.06
     Make
    0.06
     من
    0.06
     파인더
    0.05
     निजा
    0.05
    You
    0.05
    Activations Density 0.000%

    No Known Activations