© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76019
    Prev
    Next
    INDEX
    Explanations

    you may not

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting software license boilerplate text, especially occurrences of the word “License” in license headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ließ
    -0.79
    Recursive
    -0.79
     Recursive
    -0.78
    yok
    -0.78
     planific
    -0.76
     Official
    -0.74
     seront
    -0.74
    Barrett
    -0.74
    jabi
    -0.73
    шев
    -0.73
    POSITIVE LOGITS
     không
    0.81
     couldn
    0.81
     not
    0.81
     szczy
    0.79
    章节错误
    0.79
    Choose
    0.76
     Wouldn
    0.76
    طيع
    0.75
     sovereignty
    0.75
    詳しくは
    0.75
    Activations Density 0.182%

    No Known Activations