© 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. 115832
    Prev
    Next
    INDEX
    Explanations

    dot or slash separators

    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
     trailbl
    -0.07
     অধিকাংশ
    -0.07
     provide
    -0.07
    每一個
    -0.06
     interstitial
    -0.06
    스는
    -0.06
     معظم
    -0.06
     جميع
    -0.06
     Ζ
    -0.06
    Heroes
    -0.06
    POSITIVE LOGITS
     किनार
    0.06
    ore
    0.06
     it
    0.06
    pla
    0.05
    tests
    0.05
    κρι
    0.05
    ėl
    0.05
     terlebih
    0.05
     ми
    0.05
     astfel
    0.05
    Activations Density 0.001%

    No Known Activations