© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118994
    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
     one
    -0.06
    缜
    -0.06
     estimating
    -0.06
     sarà
    -0.06
    縝
    -0.06
     będzie
    -0.06
     nuestras
    -0.06
     πληροφο
    -0.06
    ucionales
    -0.06
     বিশ্রাম
    -0.05
    POSITIVE LOGITS
    Create
    0.07
    choose
    0.06
    ໃນ
    0.06
    keep
    0.06
     様
    0.05
     Многие
    0.05
     найбільш
    0.05
     mankind
    0.05
     ቲ
    0.05
     Lon
    0.05
    Activations Density 0.000%

    No Known Activations