© 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. 116235
    Prev
    Next
    INDEX
    Explanations

    coding or configuration instructions

    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
    নিতে
    -0.06
     zodat
    -0.06
     unusually
    -0.06
     really
    -0.06
     shiny
    -0.06
     davvero
    -0.06
    一路
    -0.06
    အ
    -0.06
     готова
    -0.06
    我觉得
    -0.06
    POSITIVE LOGITS
     tersebut
    0.07
     หรือ
    0.06
     العديد
    0.06
     before
    0.06
     generated
    0.06
     многие
    0.06
     many
    0.06
     некоторые
    0.06
     could
    0.06
     cientos
    0.06
    Activations Density 0.013%

    No Known Activations