© 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. 129299
    Prev
    Next
    INDEX
    Explanations

    javascript runtime errors

    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
    夫妻
    -0.07
    boat
    -0.07
    斕
    -0.06
    夫婦
    -0.06
     tuli
    -0.06
     pasangan
    -0.06
    让自己
    -0.06
     мебели
    -0.06
    EXAMPLE
    -0.06
     কমিশনের
    -0.06
    POSITIVE LOGITS
     постепенно
    0.06
    ത്തിനും
    0.06
     gradually
    0.06
    न्तु
    0.06
     identified
    0.05
     these
    0.05
    these
    0.05
     ਲੋ
    0.05
     vad
    0.05
    漸
    0.05
    Activations Density 0.012%

    No Known Activations