© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129684
    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
     점점
    -0.07
     Getting
    -0.06
     гораздо
    -0.06
     recipiente
    -0.06
    Getting
    -0.06
    getting
    -0.06
     Helping
    -0.06
    Г
    -0.06
     crazy
    -0.06
     Για
    -0.06
    POSITIVE LOGITS
     to
    0.07
    stitution
    0.07
     unless
    0.06
     tea
    0.06
     groundbreaking
    0.06
    0.06
     encompassing
    0.06
     revered
    0.06
     beds
    0.05
    льзя
    0.05
    Activations Density 0.000%

    No Known Activations