© 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. 128203
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles followed by nouns

    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
     which
    -0.07
     
    -0.07
     viable
    -0.06
    哪個
    -0.06
     "
    -0.06
     WHICH
    -0.06
    lular
    -0.06
     the
    -0.06
    哪个
    -0.06
    лук
    -0.06
    POSITIVE LOGITS
     ಹಾಗೂ
    0.07
     এমনকি
    0.06
     دائما
    0.06
     امیر
    0.06
     شخص
    0.06
     मूत्र
    0.06
     برای
    0.06
     বুদ্ধ
    0.06
    gyro
    0.06
     અને
    0.06
    Activations Density 0.050%

    No Known Activations