© 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. 116559
    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
    Encycl
    -0.06
    ใช้งาน
    -0.06
     ...(
    -0.06
     filmpje
    -0.06
     engagement
    -0.06
     aantal
    -0.06
    ENG
    -0.06
    𝘔
    -0.06
     erős
    -0.06
    関
    -0.06
    POSITIVE LOGITS
    结束后
    0.07
    仍在
    0.07
     monitoring
    0.06
    믿
    0.06
    仍然
    0.06
    ँकि
    0.06
    ?).
    0.06
     종료
    0.06
     equipe
    0.06
    婢
    0.06
    Activations Density 0.000%

    No Known Activations