© 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. 128592
    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
     accept
    -0.07
     acceptable
    -0.07
     semuanya
    -0.06
     all
    -0.06
     전부
    -0.06
    acceptable
    -0.06
     분석
    -0.06
     максима
    -0.06
     wszystkie
    -0.06
     všechny
    -0.06
    POSITIVE LOGITS
     that
    0.06
     将
    0.06
    日
    0.06
     acus
    0.06
     сотрудни
    0.06
     inizi
    0.06
     collaborated
    0.06
     cultivated
    0.06
     antagonism
    0.06
    将
    0.06
    Activations Density 0.000%

    No Known Activations