© 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. 128975
    Prev
    Next
    INDEX
    Explanations

    academic departments and fields

    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
     دانشج
    -0.07
     SCH
    -0.06
    ,(
    -0.06
    campus
    -0.06
    constraintStart
    -0.06
    னமாக
    -0.06
    ":(
    -0.06
     Studenten
    -0.06
    的学生
    -0.06
    Mismatch
    -0.06
    POSITIVE LOGITS
    同樣
    0.07
    女性
    0.07
    送料無料
    0.07
     erne
    0.06
     wiederum
    0.06
     उत्पीड़न
    0.06
    २
    0.06
     penjualan
    0.06
     ürün
    0.06
     durations
    0.06
    Activations Density 0.018%

    No Known Activations