© 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. 117210
    Prev
    Next
    INDEX
    Explanations

    let followed by a variable

    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
     domande
    -0.06
     biztos
    -0.06
    atı
    -0.06
     discussions
    -0.06
    blonde
    -0.06
     जुन
    -0.06
     ഉണ്ട്
    -0.06
     Văn
    -0.06
     leider
    -0.06
     elec
    -0.05
    POSITIVE LOGITS
     idiosync
    0.06
     (!)
    0.06
     исключительно
    0.06
     واحدة
    0.06
     parishioners
    0.06
     RE
    0.06
     are
    0.06
     peculiarity
    0.06
    ด้วย
    0.06
     artifacts
    0.06
    Activations Density 0.003%

    No Known Activations