© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128918
    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
     souvent
    -0.09
     typically
    -0.08
     usually
    -0.08
    usually
    -0.08
     geralmente
    -0.08
     often
    -0.07
     genellikle
    -0.07
    通常
    -0.07
     généralement
    -0.07
    often
    -0.07
    POSITIVE LOGITS
    assati
    0.06
     எடுத்துக்
    0.06
     Except
    0.06
     إنشاء
    0.06
     эти
    0.05
     इन
    0.05
     these
    0.05
     for
    0.05
     التر
    0.05
    सुद्धा
    0.05
    Activations Density 0.000%

    No Known Activations