© 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. 116444
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or variables

    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
     někter
    -0.08
    ;
    -0.08
     некоторых
    -0.08
    某些
    -0.07
     بعض
    -0.07
     restricts
    -0.07
     niektor
    -0.07
     bazı
    -0.07
     برخی
    -0.07
     усіх
    -0.06
    POSITIVE LOGITS
    まで
    0.07
     with
    0.07
     six
    0.06
     by
    0.06
     without
    0.06
     etc
    0.06
     By
    0.06
     šest
    0.06
    까지
    0.06
    ടി
    0.06
    Activations Density 0.011%

    No Known Activations