© 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. 116615
    Prev
    Next
    INDEX
    Explanations

    introduction or title markers

    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
    State
    -0.07
     Alsace
    -0.06
    itaea
    -0.06
     State
    -0.06
     स्टेट
    -0.06
     employing
    -0.06
     வழிபட்ட
    -0.06
    废
    -0.06
     attains
    -0.05
     specifying
    -0.05
    POSITIVE LOGITS
    François
    0.07
     WILL
    0.07
     эволю
    0.06
     innerhalb
    0.06
     внутри
    0.06
     आगे
    0.06
     lunga
    0.06
     irão
    0.06
     lógica
    0.06
    WILL
    0.06
    Activations Density 0.007%

    No Known Activations