© 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. 128791
    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
     deres
    -0.06
    П
    -0.06
     with
    -0.06
     Convention
    -0.06
     از
    -0.06
     será
    -0.06
     على
    -0.06
     भला
    -0.06
     Regel
    -0.06
    cture
    -0.06
    POSITIVE LOGITS
     মাস্টার
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    在那
    0.06
     kū
    0.06
    âme
    0.06
     imaginar
    0.06
    &=\
    0.05
    '}}>
    0.05
    дная
    0.05
     nutritious
    0.05
    Activations Density 0.000%

    No Known Activations