© 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. 117547
    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
     miễn
    -0.06
    更多
    -0.06
    㕷
    -0.06
     vocalist
    -0.06
     mía
    -0.06
     mniej
    -0.06
     Shimano
    -0.06
     nő
    -0.06
     انسٹ
    -0.06
     fő
    -0.06
    POSITIVE LOGITS
     admittance
    0.07
     पढ़कर
    0.06
     intervened
    0.06
     ยัง
    0.06
     summing
    0.06
     volut
    0.06
     interconnect
    0.06
     перечис
    0.06
     протяжении
    0.06
     described
    0.06
    Activations Density 0.000%

    No Known Activations