© 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. 130576
    Prev
    Next
    INDEX
    Explanations

    electron beam microscopy

    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
     Saudi
    -0.06
    Saudi
    -0.06
    यी
    -0.06
     ایم
    -0.06
     Adventist
    -0.06
     Near
    -0.06
     regist
    -0.06
    filePath
    -0.05
    উন্ট
    -0.05
     타입
    -0.05
    POSITIVE LOGITS
     (-)
    0.07
    시간
    0.06
    ﹋
    0.06
     warehouses
    0.06
    Suppress
    0.06
     ಹಿಂದ
    0.06
    -:
    0.06
     maha
    0.06
    ಲೆ
    0.06
    heavy
    0.06
    Activations Density 0.003%

    No Known Activations