© 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. 129539
    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
    咛
    -0.07
    standard
    -0.07
     நூற்றாண்ட
    -0.06
    turno
    -0.06
     حضور
    -0.06
     veritable
    -0.06
     ژوند
    -0.06
    标准
    -0.06
     标准
    -0.06
     aktiv
    -0.06
    POSITIVE LOGITS
     Cheesecake
    0.07
     uč
    0.06
     يلي
    0.05
    Doesn
    0.05
     그렇게
    0.05
     Міні
    0.05
     Doesn
    0.05
    heu
    0.05
    ylen
    0.05
    :)
    0.05
    Activations Density 0.000%

    No Known Activations