© 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. 118358
    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
    nonumber
    -0.06
    son
    -0.06
     flaw
    -0.06
    d
    -0.05
    ogeneous
    -0.05
    SON
    -0.05
     advisors
    -0.05
    Arch
    -0.05
    Bed
    -0.05
    षिक
    -0.05
    POSITIVE LOGITS
     লেখক
    0.07
     jadi
    0.06
    路径
    0.06
     опас
    0.06
     complied
    0.06
     постоянно
    0.06
     быстро
    0.06
    🛹
    0.06
     DataTable
    0.06
    круг
    0.06
    Activations Density 0.000%

    No Known Activations