© 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. 120642
    Prev
    Next
    INDEX
    Explanations

    JSON configuration

    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
    verbose
    -0.06
     goes
    -0.06
    ጢ
    -0.06
    iotensin
    -0.06
     everything
    -0.06
     geht
    -0.06
    reform
    -0.06
     dehydrogenase
    -0.06
    Espagne
    -0.06
     लेना
    -0.06
    POSITIVE LOGITS
     picturesque
    0.06
     hinder
    0.06
     Mathematical
    0.06
     moreover
    0.05
     পরবর্তীতে
    0.05
    明显的
    0.05
     càng
    0.05
    ộn
    0.05
     blurring
    0.05
    そも
    0.05
    Activations Density 0.002%

    No Known Activations