© 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. 129853
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
    當時
    -0.06
     contemporaries
    -0.06
     당시
    -0.06
    当时
    -0.05
    χρι
    -0.05
     actuelle
    -0.05
     functioned
    -0.05
     grantees
    -0.05
     rh
    -0.05
    当时的
    -0.05
    POSITIVE LOGITS
    無法
    0.07
    差不多
    0.07
     เวอร์ชั่น
    0.07
     Ahí
    0.07
    无法
    0.07
     wages
    0.06
     آتا
    0.06
     oon
    0.06
    ・・・・
    0.06
    不足
    0.06
    Activations Density 0.001%

    No Known Activations