© 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. 129756
    Prev
    Next
    INDEX
    Explanations

    **HTML Tags and UI Elements**

    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
     עם
    -0.08
     với
    -0.07
     with
    -0.07
     dengan
    -0.07
     and
    -0.07
     avec
    -0.06
     préparations
    -0.06
     aperture
    -0.06
     ترکیب
    -0.06
    と一緒に
    -0.06
    POSITIVE LOGITS
     embracing
    0.06
    levels
    0.06
    :
    0.06
     decreasing
    0.05
     dismin
    0.05
     イタリア
    0.05
    cza
    0.05
     nobles
    0.05
     torn
    0.05
    ibana
    0.05
    Activations Density 0.001%

    No Known Activations