© 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. 129231
    Prev
    Next
    INDEX
    Explanations

    Vendors, Introduction, Q, Genetic

    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
     indign
    -0.07
     efficient
    -0.06
    নব
    -0.06
     helpful
    -0.06
     použití
    -0.06
     newcomers
    -0.06
     expanding
    -0.06
     zero
    -0.06
    espace
    -0.06
     impressively
    -0.06
    POSITIVE LOGITS
    通常
    0.06
     обычно
    0.06
     Buyer
    0.06
     közvet
    0.06
    普段
    0.06
     přímo
    0.06
     സർ
    0.06
     معمول
    0.06
     ఆయన
    0.06
    Started
    0.06
    Activations Density 0.006%

    No Known Activations