© 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. 129646
    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
     was
    -0.08
     기본적인
    -0.07
    several
    -0.07
     several
    -0.06
     spelt
    -0.06
    了几
    -0.06
     related
    -0.06
    了他的
    -0.06
     jeho
    -0.06
    了他
    -0.06
    POSITIVE LOGITS
     first
    0.06
    ↵
    0.06
     finan
    0.06
     世界
    0.06
    最初に
    0.06
     र
    0.06
     मीट
    0.06
    first
    0.06
     FIRST
    0.05
     இங்கே
    0.05
    Activations Density 0.000%

    No Known Activations