© 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. 119797
    Prev
    Next
    INDEX
    Explanations

    [@B] or [@CR]

    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
     आणखी
    -0.06
     による
    -0.06
    raison
    -0.06
     याचा
    -0.06
     ചെയ്തി
    -0.06
    লাপ
    -0.06
    의
    -0.06
     ఏర్ప
    -0.06
     interfering
    -0.06
     often
    -0.05
    POSITIVE LOGITS
     ध
    0.06
    （
    0.06
    typical
    0.06
    modell
    0.06
     wszystkich
    0.05
     fairway
    0.05
    新型
    0.05
     Greens
    0.05
    ！
    0.05
     तीनों
    0.05
    Activations Density 0.001%

    No Known Activations