© 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. 128619
    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
    AH
    -0.06
     независимо
    -0.06
     of
    -0.06
     связан
    -0.06
     очень
    -0.06
     как
    -0.06
     надо
    -0.06
    以
    -0.06
    AB
    -0.06
     डाले
    -0.05
    POSITIVE LOGITS
     comfortably
    0.07
     কিংবা
    0.06
    安心
    0.06
     discomfort
    0.06
     mutta
    0.06
     thirteenth
    0.06
    boiled
    0.06
     compounded
    0.06
     ধরনের
    0.06
     fikk
    0.06
    Activations Density 0.000%

    No Known Activations