© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 127943
    Prev
    Next
    INDEX
    Explanations

    video apparatus, imaging, posts, invention

    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
    Negative Logits
    =>
    -0.07
    гая
    -0.06
    ='
    -0.06
    :
    -0.06
    default
    -0.06
     one
    -0.06
     greatest
    -0.06
     à
    -0.06
     our
    -0.06
    뭍
    -0.06
    POSITIVE LOGITS
    uncu
    0.07
     আনুগত্য
    0.06
     അദ്ദേഹ
    0.06
     відноси
    0.06
     карка
    0.06
    വേഷ
    0.06
     ප්‍රති
    0.06
    yny
    0.05
     Worm
    0.05
     সূত্র
    0.05
    Activations Density 0.001%

    No Known Activations