© 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. 116328
    Prev
    Next
    INDEX
    Explanations

    AvailableAirspeedAzureKeyboardOpenProjectDevelopingDM

    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
     acquaintance
    -0.06
     wont
    -0.06
    unto
    -0.06
     prettier
    -0.06
     airport
    -0.06
     restful
    -0.06
     নিয়ন্ত্র
    -0.05
     kui
    -0.05
     নূতন
    -0.05
     कराय
    -0.05
    POSITIVE LOGITS
     nếu
    0.07
     если
    0.06
    recently
    0.06
     Если
    0.06
     आई
    0.06
     недавно
    0.06
    データを
    0.06
    बीर
    0.06
    我们要
    0.06
    Если
    0.06
    Activations Density 0.002%

    No Known Activations