© 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. 119674
    Prev
    Next
    INDEX
    Explanations

    units and symbols in scientific contexts

    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
    就是
    -0.07
    她是
    -0.07
    르는
    -0.07
    所有
    -0.07
    但是在
    -0.06
     就是
    -0.06
    મો
    -0.06
     בין
    -0.06
    可能是
    -0.06
     justo
    -0.06
    POSITIVE LOGITS
    develop
    0.06
     নিষ্
    0.06
     PROPERTIES
    0.06
     status
    0.06
    Develop
    0.06
     Avrupa
    0.06
     gece
    0.05
    ությ
    0.05
    PHYS
    0.05
    ของคุณ
    0.05
    Activations Density 0.001%

    No Known Activations