© 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. 129001
    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
     also
    -0.07
     prev
    -0.06
     extraordinaire
    -0.06
     좀
    -0.06
    🛡
    -0.06
     전체
    -0.06
     더욱
    -0.06
    आख
    -0.06
     Suff
    -0.06
     공식
    -0.05
    POSITIVE LOGITS
     twenty
    0.07
     theyre
    0.06
     когда
    0.06
    quando
    0.06
     concentration
    0.06
     हो
    0.06
    тической
    0.06
    就是一个
    0.06
     thirty
    0.06
     forty
    0.06
    Activations Density 0.000%

    No Known Activations