© 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. 117337
    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
     had
    -0.07
     ahora
    -0.07
     now
    -0.07
     trzech
    -0.07
     داشت
    -0.06
     haría
    -0.06
     kini
    -0.06
     drei
    -0.06
    uan
    -0.06
     three
    -0.06
    POSITIVE LOGITS
     your
    0.08
     votre
    0.06
    your
    0.06
    以及
    0.06
    你的
    0.06
    Your
    0.06
     Your
    0.06
     surprising
    0.06
     sportswear
    0.06
     ваш
    0.06
    Activations Density 0.000%

    No Known Activations