© 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. 116687
    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
     что
    -0.07
    。
    -0.06
     that
    -0.06
     high
    -0.06
     from
    -0.06
     five
    -0.06
    正式
    -0.06
     meskipun
    -0.06
     which
    -0.06
     karena
    -0.06
    POSITIVE LOGITS
     of
    0.07
     the
    0.07
     alberga
    0.06
     vitally
    0.06
     irrepar
    0.06
    itipi
    0.06
     remarque
    0.06
    9
    0.06
     DHCP
    0.06
     প্রতিনি
    0.06
    Activations Density 0.000%

    No Known Activations