© 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. 128409
    Prev
    Next
    INDEX
    Explanations

    errors, exceptions, directions, downloading

    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
    mainly
    -0.07
     comme
    -0.07
    脇
    -0.06
    起こ
    -0.06
     주요
    -0.06
    特に
    -0.06
     mainly
    -0.06
     który
    -0.06
     거고
    -0.06
     الضر
    -0.06
    POSITIVE LOGITS
     आफ
    0.06
     Of
    0.06
     вместо
    0.05
    ดังกล่าว
    0.05
     ALL
    0.05
    <0xB8>
    0.05
    එ
    0.05
    ')){
    0.05
     не
    0.05
     সতর্কতা
    0.05
    Activations Density 0.001%

    No Known Activations