© 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. 116258
    Prev
    Next
    INDEX
    Explanations

    related to numbers or lists

    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
     durante
    -0.07
     वास्तव
    -0.07
    অনেক
    -0.06
     během
    -0.06
     realmente
    -0.06
     했는데
    -0.06
     dauer
    -0.06
     действительно
    -0.06
     not
    -0.06
     tokom
    -0.06
    POSITIVE LOGITS
     on
    0.07
     programming
    0.06
     programas
    0.06
     programu
    0.06
     carat
    0.06
     ปุ่ม
    0.06
     exploits
    0.06
     programs
    0.06
    㕫
    0.06
     precedent
    0.06
    Activations Density 0.002%

    No Known Activations