© 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. 129508
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
     notable
    -0.06
    기와
    -0.06
     fairly
    -0.06
     adopting
    -0.06
     substantial
    -0.06
    |=|
    -0.06
     noteworthy
    -0.06
     दूसरी
    -0.06
     ..........
    -0.06
     differing
    -0.06
    POSITIVE LOGITS
     Tiktok
    0.06
     şeyler
    0.06
     Piotr
    0.06
     전체
    0.06
    cknowled
    0.06
    તે
    0.06
     mulberry
    0.06
     ഓരോ
    0.06
    दुनिया
    0.05
     towns
    0.05
    Activations Density 0.001%

    No Known Activations