© 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. 116353
    Prev
    Next
    INDEX
    Explanations

    established since or located

    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
    ដើម្បី
    -0.08
     żad
    -0.07
     nenhum
    -0.07
     nenhuma
    -0.07
     obses
    -0.07
    什么是
    -0.07
     wordpress
    -0.06
     обеспечивает
    -0.06
     কোনও
    -0.06
     تړ
    -0.06
    POSITIVE LOGITS
     one
    0.08
     和
    0.07
     が
    0.07
     it
    0.06
     inconspicuous
    0.06
     を
    0.06
     的
    0.06
     One
    0.06
     ア
    0.06
    It
    0.05
    Activations Density 0.107%

    No Known Activations