© 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. 129307
    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
     तुमच्या
    -0.07
     данной
    -0.06
     данных
    -0.06
     ১ম
    -0.06
     sui
    -0.06
     данного
    -0.06
     dessa
    -0.06
     ನಡುವ
    -0.06
     sassy
    -0.06
     desenvolvimento
    -0.06
    POSITIVE LOGITS
    的一切
    0.06
     conditionally
    0.06
    vee
    0.06
     innumerable
    0.06
    fib
    0.05
     VAL
    0.05
     familiarize
    0.05
    辩
    0.05
     प्रौद्योगिकी
    0.05
     দলকে
    0.05
    Activations Density 0.000%

    No Known Activations