© 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. 130644
    Prev
    Next
    INDEX
    Explanations

    Jake Jones

    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
     dwie
    -0.07
     the
    -0.06
     a
    -0.06
     czyli
    -0.06
     standards
    -0.06
    祇
    -0.06
     Allgemeine
    -0.06
     suunn
    -0.06
    于
    -0.06
     получила
    -0.05
    POSITIVE LOGITS
     to
    0.08
     associated
    0.07
     οπο
    0.06
     বিভাগের
    0.06
     (
    0.06
     associé
    0.06
     rural
    0.06
     aggregated
    0.06
     attributes
    0.06
     कंफ
    0.06
    Activations Density 0.001%

    No Known Activations