© 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. 129859
    Prev
    Next
    INDEX
    Explanations

    placing items into containers

    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
     באמצעות
    -0.06
     futile
    -0.06
     შეი
    -0.06
    すごく
    -0.06
     сформи
    -0.06
     yaparak
    -0.06
     basados
    -0.06
     resultat
    -0.06
     результатом
    -0.06
    ⒋
    -0.06
    POSITIVE LOGITS
    arrêt
    0.07
     vary
    0.06
    等等
    0.06
     anderen
    0.06
    规划
    0.06
    ficha
    0.06
     and
    0.06
     Bronco
    0.06
     can
    0.05
     prefers
    0.05
    Activations Density 0.004%

    No Known Activations