© 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. 116858
    Prev
    Next
    INDEX
    Explanations

    testing, test, TDD, xml, big, porous

    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
     at
    -0.08
     organiz
    -0.07
    organiz
    -0.06
    组织的
    -0.06
     кое
    -0.06
     компонен
    -0.06
     components
    -0.05
    团
    -0.05
    deleg
    -0.05
     no
    -0.05
    POSITIVE LOGITS
    creating
    0.07
     converting
    0.06
     subsequent
    0.06
     ridiculously
    0.06
     insanely
    0.06
     aesthetically
    0.06
    校验
    0.06
     Where
    0.06
     maintaining
    0.06
     automated
    0.06
    Activations Density 0.008%

    No Known Activations