© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128634
    Prev
    Next
    INDEX
    Explanations

    Q: Ottoman Brandon Comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     تازه
    -0.07
    鴳
    -0.07
     poser
    -0.07
     الحالي
    -0.07
     अंदाजा
    -0.07
    clear
    -0.06
     boş
    -0.06
     nowych
    -0.06
     fragrances
    -0.06
     nowego
    -0.06
    POSITIVE LOGITS
     meliputi
    0.06
    Document
    0.05
    Diane
    0.05
    方向
    0.05
    รวม
    0.05
     muscle
    0.05
    実際
    0.05
     салу
    0.05
     францу
    0.05
     পুঁজিব
    0.05
    Activations Density 0.001%

    No Known Activations