© 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. 128472
    Prev
    Next
    INDEX
    Explanations

    code block markers, programming constructs

    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
     podľa
    -0.06
    ที่เรา
    -0.06
    한다는
    -0.06
     Франции
    -0.06
     Snowy
    -0.06
    щата
    -0.06
    Kita
    -0.06
    较高的
    -0.06
    PDA
    -0.06
     কিন্তু
    -0.06
    POSITIVE LOGITS
    0
    0.06
    overview
    0.06
    signatures
    0.06
     learners
    0.06
     educating
    0.06
     Glas
    0.06
    стви
    0.05
     passag
    0.05
    doctype
    0.05
     bringing
    0.05
    Activations Density 0.001%

    No Known Activations