© 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. 116898
    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
    一些
    -0.06
    一半
    -0.06
     udah
    -0.06
    parsers
    -0.06
     careless
    -0.06
     انسان
    -0.06
     είναι
    -0.06
     sudah
    -0.06
     name
    -0.06
     membuat
    -0.06
    POSITIVE LOGITS
     영국
    0.06
    只见
    0.06
     yrs
    0.06
     bronchitis
    0.06
     ब्रिटेन
    0.06
     শুধ
    0.06
     entdeck
    0.06
    মধ্যে
    0.05
     disabilities
    0.05
     இருக்கலாம்
    0.05
    Activations Density 0.000%

    No Known Activations