© 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. 128771
    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
     think
    -0.07
    think
    -0.06
     vuelva
    -0.06
    データ
    -0.06
     thinks
    -0.06
     bovine
    -0.06
    யி
    -0.06
     definitively
    -0.05
    そのため
    -0.05
     Tricks
    -0.05
    POSITIVE LOGITS
    有机会
    0.07
     quizás
    0.06
     intriguing
    0.06
     portability
    0.06
     possibilité
    0.06
     lehetős
    0.06
    ドラゴン
    0.06
     hopefully
    0.06
    ُر
    0.06
     সম্মিল
    0.06
    Activations Density 0.000%

    No Known Activations