© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118578
    Prev
    Next
    INDEX
    Explanations

    be / is / are

    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
    న్నో
    -0.06
     ኣብ
    -0.05
     먼
    -0.05
     ayarl
    -0.05
    App
    -0.05
     deftly
    -0.05
     showdown
    -0.05
    レポート
    -0.05
     обеспечения
    -0.05
     नॉट
    -0.05
    POSITIVE LOGITS
     votre
    0.06
    dynamic
    0.06
     pomocy
    0.06
     pentru
    0.06
    自己
    0.06
     гости
    0.06
    错了
    0.06
    ায়ার
    0.06
     szczę
    0.06
     todas
    0.05
    Activations Density 0.004%

    No Known Activations