© 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. 120617
    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
    際に
    -0.07
     mittels
    -0.06
    Lik
    -0.06
     sfrutt
    -0.06
     using
    -0.06
     harnessing
    -0.06
     hatte
    -0.06
     zwei
    -0.06
    際の
    -0.06
     путем
    -0.06
    POSITIVE LOGITS
    の間
    0.06
     participar
    0.06
     representing
    0.06
    时间的
    0.06
     Different
    0.06
     participe
    0.06
    犟
    0.06
     podle
    0.06
    变的
    0.06
     neo
    0.06
    Activations Density 0.000%

    No Known Activations