© 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. 128995
    Prev
    Next
    INDEX
    Explanations

    quantities or collections

    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
     constituted
    -0.06
    grupo
    -0.06
    喊
    -0.06
     terrib
    -0.06
     gotten
    -0.06
     until
    -0.06
     will
    -0.06
     unmarked
    -0.05
    র্মে
    -0.05
     lipid
    -0.05
    POSITIVE LOGITS
     allgemein
    0.07
     của
    0.06
     each
    0.06
     chaque
    0.06
    ea
    0.06
    Each
    0.06
     mengikuti
    0.06
    each
    0.06
     și
    0.06
    elom
    0.06
    Activations Density 0.038%

    No Known Activations