© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120317
    Prev
    Next
    INDEX
    Explanations

    Male pattern routing msbuild xaml

    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
     boutiques
    -0.06
     arouse
    -0.06
     نئے
    -0.06
     रिलेटेड
    -0.06
    म्ह
    -0.06
    itional
    -0.06
     commence
    -0.06
    ान्स
    -0.06
     উচ্চ
    -0.06
     Uran
    -0.06
    POSITIVE LOGITS
     NULL
    0.07
    .
    0.06
     contexts
    0.06
     কমিয়ে
    0.06
     kontakt
    0.06
     notizia
    0.06
     THANK
    0.05
    NULL
    0.05
    iz
    0.05
     dokument
    0.05
    Activations Density 0.001%

    No Known Activations