© 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. 116461
    Prev
    Next
    INDEX
    Explanations

    election that

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ตั้ง
    -0.06
     legally
    -0.06
     সাধারণভাবে
    -0.06
     which
    -0.06
     edific
    -0.05
     jedan
    -0.05
     invigor
    -0.05
     шпа
    -0.05
    quen
    -0.05
     setToDefault
    -0.05
    POSITIVE LOGITS
    上記の
    0.06
    two
    0.06
    家
    0.06
    两个
    0.06
    Anthony
    0.06
    more
    0.06
    前面的
    0.06
    上述
    0.06
     могут
    0.06
     quis
    0.06
    Activations Density 0.037%

    No Known Activations