© 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. 128970
    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
    This
    -0.07
     আপাত
    -0.07
     using
    -0.06
     varios
    -0.06
     supplementing
    -0.06
    Up
    -0.06
     twofold
    -0.06
     this
    -0.06
     emphasizing
    -0.06
     अनुभव
    -0.06
    POSITIVE LOGITS
     વચ્ચે
    0.07
     между
    0.06
     ainda
    0.06
     bandage
    0.06
    ständ
    0.06
     ακόμη
    0.06
     खड़े
    0.06
     indiquer
    0.06
     jagged
    0.06
     petición
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.