© 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. 121014
    Prev
    Next
    INDEX
    Explanations

    court of appeals and filings

    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
    ⏬
    -0.06
     thậm
    -0.06
    甚至是
    -0.06
     even
    -0.06
     dinast
    -0.06
     dint
    -0.05
    🈺
    -0.05
     ഏറ്റവും
    -0.05
     ultim
    -0.05
     prestation
    -0.05
    POSITIVE LOGITS
     لذلك
    0.06
     бы
    0.06
     kaikki
    0.06
    全ての
    0.06
     foreseen
    0.06
    leicht
    0.06
    ვნ
    0.06
    ného
    0.06
     slimy
    0.06
     رو
    0.06
    Activations Density 0.009%

    No Known Activations