© 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. 128462
    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
     never
    -0.08
    un
    -0.06
     jamais
    -0.06
    如果
    -0.06
    可能的
    -0.06
     calculated
    -0.06
     NEVER
    -0.06
     rid
    -0.06
    或者
    -0.06
    ogli
    -0.06
    POSITIVE LOGITS
     срав
    0.07
     الموجود
    0.06
     تحتوي
    0.06
     رفتار
    0.06
     abnormalities
    0.06
     cocina
    0.06
    と同様
    0.06
     Vegetarian
    0.06
    वेशन
    0.06
     Citibank
    0.06
    Activations Density 0.000%

    No Known Activations