© 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. 128491
    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
    accueil
    -0.07
     آج
    -0.06
     madres
    -0.06
    今天
    -0.06
    这些
    -0.06
     माध्यमा
    -0.06
    configurations
    -0.06
     பெண்கள்
    -0.06
    anticipated
    -0.06
    今天的
    -0.06
    POSITIVE LOGITS
     White
    0.07
    เขียน
    0.06
     সত্ত
    0.06
     adrenaline
    0.06
     requires
    0.06
     Wild
    0.05
     إص
    0.05
    -
    0.05
     and
    0.05
    White
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.