© 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. 118386
    Prev
    Next
    INDEX
    Explanations

    QT, III, Slash, Kirk, Ne

    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
    dm
    -0.06
     isActive
    -0.06
     Delivery
    -0.06
     Ruhe
    -0.05
     direct
    -0.05
    prefix
    -0.05
     অধিকাংশ
    -0.05
     Durable
    -0.05
     directe
    -0.05
     actually
    -0.05
    POSITIVE LOGITS
    ച്ചി
    0.06
    กฏ
    0.06
    學校
    0.06
    模特
    0.06
    娉
    0.06
     ingredientes
    0.06
     Komponenten
    0.06
     prominently
    0.06
     önemli
    0.06
    роки
    0.06
    Activations Density 0.014%

    No Known Activations