© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129792
    Prev
    Next
    INDEX
    Explanations

    recipe instructions

    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
     kitchens
    -0.07
     நவ
    -0.06
     keď
    -0.06
    胃
    -0.06
     když
    -0.06
     ለ
    -0.06
     dining
    -0.06
     soln
    -0.06
     ถ้า
    -0.06
    ppled
    -0.05
    POSITIVE LOGITS
     awesome
    0.07
     නිසා
    0.06
     всего
    0.06
    苎
    0.06
     ಖರೀ
    0.06
     egyszerű
    0.06
     sogar
    0.06
    anzi
    0.06
     পরিশ
    0.06
    强大的
    0.06
    Activations Density 0.019%

    No Known Activations