© 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. 120024
    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
     start
    -0.07
     parte
    -0.06
    のでは
    -0.06
    기로
    -0.06
    まとめ
    -0.06
     일부
    -0.06
     ofert
    -0.06
     together
    -0.06
     laboratories
    -0.06
     sizes
    -0.06
    POSITIVE LOGITS
     probs
    0.06
     OPPORT
    0.06
    ভূতির
    0.06
    Opportunities
    0.06
     trong
    0.06
    进攻
    0.05
     মার্চের
    0.05
     probably
    0.05
     meinem
    0.05
    sü
    0.05
    Activations Density 0.003%

    No Known Activations