© 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. 130273
    Prev
    Next
    INDEX
    Explanations

    random forest and partitioning

    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
     façade
    -0.07
     проект
    -0.06
     அவர்களுடைய
    -0.06
     projekt
    -0.06
     Projekt
    -0.06
     mauvaise
    -0.06
    rég
    -0.06
     progetti
    -0.06
    heva
    -0.06
     jų
    -0.06
    POSITIVE LOGITS
     during
    0.07
     Tijdens
    0.07
     מפ
    0.06
     गेंदों
    0.06
     sırasında
    0.06
     일으
    0.06
    いや
    0.06
     ওভারে
    0.06
     Python
    0.06
     mortality
    0.06
    Activations Density 0.003%

    No Known Activations