© 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. 116554
    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
     здесь
    -0.06
     activist
    -0.06
     hänen
    -0.06
     Rebel
    -0.06
     @
    -0.06
     신청
    -0.06
    certificate
    -0.05
     заяв
    -0.05
    berg
    -0.05
     (
    -0.05
    POSITIVE LOGITS
     విభ
    0.07
    ाइब
    0.07
     اچھا
    0.06
     chủng
    0.06
    小时
    0.06
    يء
    0.06
     subdivided
    0.06
     آگے
    0.06
     punctuated
    0.06
    Unable
    0.06
    Activations Density 0.000%

    No Known Activations