© 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. 128977
    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
     لیون
    -0.06
    这个
    -0.06
     рит
    -0.06
    今
    -0.06
     produced
    -0.06
     diesen
    -0.06
     petrol
    -0.06
     이런
    -0.06
     Miocene
    -0.06
     Produced
    -0.05
    POSITIVE LOGITS
     three
    0.08
     hawk
    0.07
     attaining
    0.07
     tiga
    0.07
     drei
    0.06
    とは
    0.06
     establishing
    0.06
     enhanced
    0.06
     nifty
    0.06
     camaraderie
    0.06
    Activations Density 0.000%

    No Known Activations