© 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. 116266
    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
     and
    -0.08
     ข้อ
    -0.07
    ^{
    -0.06
    防御
    -0.06
     Consortium
    -0.06
     ath
    -0.06
     Agosto
    -0.06
    電荷
    -0.06
    ,+\
    -0.06
     https
    -0.06
    POSITIVE LOGITS
     situaciones
    0.06
     मॉ
    0.06
     plötzlich
    0.06
     situazioni
    0.06
     sizes
    0.06
     произо
    0.06
     الفرنس
    0.06
     размеров
    0.06
     مقابل
    0.06
     situations
    0.06
    Activations Density 0.000%

    No Known Activations