© 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. 117137
    Prev
    Next
    INDEX
    Explanations

    physics and technical terms

    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
     including
    -0.06
     termasuk
    -0.06
     সমর্থনে
    -0.06
     flares
    -0.06
     collage
    -0.06
    ラスト
    -0.06
    新生
    -0.06
     flare
    -0.06
    getter
    -0.06
     incluyendo
    -0.06
    POSITIVE LOGITS
     để
    0.06
    解决
    0.06
     žele
    0.06
     выполнять
    0.06
     prä
    0.06
     બનાવવા
    0.06
     paraly
    0.06
     numberWith
    0.06
    Games
    0.06
    financial
    0.06
    Activations Density 0.001%

    No Known Activations