© 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. 119838
    Prev
    Next
    INDEX
    Explanations

    XML and C# programming constructs

    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
     essencial
    -0.06
    otypes
    -0.06
     ingestion
    -0.06
    totally
    -0.06
     incredible
    -0.06
     ocasion
    -0.06
     Quelle
    -0.06
     fantastic
    -0.06
     असंभव
    -0.05
     importers
    -0.05
    POSITIVE LOGITS
     الكثير
    0.07
     striving
    0.06
     многим
    0.06
     start
    0.06
     প্রাক্তন
    0.06
    тился
    0.06
     disfrut
    0.06
     opening
    0.06
     인기
    0.05
     strive
    0.05
    Activations Density 0.001%

    No Known Activations