© 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. 116830
    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
    教材
    -0.06
     Microsc
    -0.06
     très
    -0.06
     दैट
    -0.06
     our
    -0.06
    naires
    -0.06
    ामुळे
    -0.06
     דו
    -0.05
     πάνω
    -0.05
    到
    -0.05
    POSITIVE LOGITS
     strengthens
    0.06
     improves
    0.06
     purportedly
    0.06
    んでも
    0.06
     unbelievable
    0.06
     বলিল
    0.06
     uttered
    0.06
    ិ
    0.06
     delivers
    0.06
     ludicrous
    0.06
    Activations Density 0.000%

    No Known Activations