© 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. 117829
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and formulas

    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
    Make
    -0.06
     derechos
    -0.06
     diritti
    -0.05
     अधीनस्थ
    -0.05
    ഞ്ച്
    -0.05
    我們會
    -0.05
    ↵↵↵
    -0.05
     Make
    -0.05
     seharusnya
    -0.05
    است
    -0.05
    POSITIVE LOGITS
     purpose
    0.07
     целью
    0.07
     Vocational
    0.06
     फैलाने
    0.06
     яго
    0.06
    जबकि
    0.06
     subroutine
    0.06
     generates
    0.06
     SPEED
    0.06
     дуже
    0.06
    Activations Density 0.042%

    No Known Activations