© 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. 119560
    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
     doesn
    -0.06
     달
    -0.06
    當時
    -0.06
    કર્
    -0.06
    ？
    -0.06
     الأعمال
    -0.05
    ...\
    -0.05
     wint
    -0.05
     مه
    -0.05
    当时
    -0.05
    POSITIVE LOGITS
    可能会
    0.07
    প্রায়
    0.07
    可能會
    0.07
     çoğu
    0.06
    🚿
    0.06
    প্রায়
    0.06
     PREMIUM
    0.06
     may
    0.06
    多く
    0.06
     குற
    0.06
    Activations Density 0.000%

    No Known Activations