© 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. 129418
    Prev
    Next
    INDEX
    Explanations

    data corruption

    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
     তিনি
    -0.06
     parameters
    -0.06
     параметры
    -0.06
    ksz
    -0.06
     கொண்டே
    -0.06
     umożliw
    -0.06
    options
    -0.06
     local
    -0.06
     param
    -0.06
     configuration
    -0.06
    POSITIVE LOGITS
     insgesamt
    0.06
     before
    0.06
     humour
    0.06
     når
    0.06
     marka
    0.06
    Ο
    0.06
     flanking
    0.06
    NSInteger
    0.06
     catech
    0.06
     συνο
    0.06
    Activations Density 0.001%

    No Known Activations