© 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. 128597
    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
    除非
    -0.06
     we
    -0.06
     guidance
    -0.06
    বর্ধ
    -0.06
     comprende
    -0.05
     pressur
    -0.05
    uri
    -0.05
     unless
    -0.05
    YOU
    -0.05
     възможно
    -0.05
    POSITIVE LOGITS
     xxx
    0.07
     XX
    0.06
     serán
    0.06
     của
    0.06
     algún
    0.06
    тились
    0.06
     undoubt
    0.06
     desta
    0.06
     ______
    0.06
     algum
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.