© 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. 116147
    Prev
    Next
    INDEX
    Explanations

    words starting sentences/clauses

    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
    ⵥ
    -0.07
     próprio
    -0.07
     which
    -0.07
     just
    -0.06
    pores
    -0.06
    ），
    -0.06
     ඔවුන්
    -0.06
     trabalho
    -0.06
     perubahan
    -0.06
     WHICH
    -0.06
    POSITIVE LOGITS
     (
    0.09
    :
    0.08
    Finally
    0.07
     ("
    0.06
     -
    0.06
     Finalmente
    0.06
     ["
    0.06
    Various
    0.06
    <
    0.06
    .:
    0.06
    Activations Density 0.016%

    No Known Activations