© 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. 120668
    Prev
    Next
    INDEX
    Explanations

    function return types or introduction

    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
     большинстве
    -0.07
     atteindre
    -0.07
     نوفمبر
    -0.07
     meisten
    -0.06
     confuse
    -0.06
     Qualquer
    -0.06
    vesti
    -0.06
    Sciences
    -0.06
    Desde
    -0.06
    ÓN
    -0.06
    POSITIVE LOGITS
    明明
    0.06
     also
    0.05
     también
    0.05
    घो
    0.05
    <0xE3>
    0.05
     abroad
    0.05
     anche
    0.05
    Also
    0.05
    also
    0.05
     ઉપરાંત
    0.05
    Activations Density 0.001%

    No Known Activations