© 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. 117507
    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
     nuovamente
    -0.07
     Ethn
    -0.07
     ক্যান্স
    -0.06
     passos
    -0.06
     vibrant
    -0.06
    呢
    -0.06
    Attempt
    -0.06
     etap
    -0.06
     tenter
    -0.06
    Provision
    -0.06
    POSITIVE LOGITS
    even
    0.06
    スタート
    0.06
     alphabetically
    0.06
    whatever
    0.06
    EVEN
    0.06
     PEM
    0.06
     auxilia
    0.06
     BEFORE
    0.06
     YOUR
    0.05
    開始
    0.05
    Activations Density 0.000%

    No Known Activations