© 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. 119383
    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
    。“
    -0.06
    如果
    -0.06
    লাই
    -0.06
    зом
    -0.06
     oleh
    -0.06
     Евгений
    -0.06
     savo
    -0.06
     Uncertain
    -0.06
     जेव्हा
    -0.06
    Data
    -0.05
    POSITIVE LOGITS
     things
    0.07
     Things
    0.07
     two
    0.07
    things
    0.07
     six
    0.07
     बिलकुल
    0.07
    tìm
    0.06
     큰
    0.06
     dingen
    0.06
     nine
    0.06
    Activations Density 0.000%

    No Known Activations