© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1408
    Prev
    Next
    INDEX
    Explanations

    code documentation licenses

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

    The main thing this neuron does is detect copyright and license boilerplate text blocks in source code.

    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
    曌
    -0.81
     alamy
    -0.81
    handel
    -0.79
     Stakeholders
    -0.79
    onCreate
    -0.79
     құ
    -0.79
    راً
    -0.78
     Ronda
    -0.78
     Boe
    -0.77
     foreseen
    -0.77
    POSITIVE LOGITS
     Saskatchewan
    1.18
     Saskatoon
    1.07
     should
    0.91
     Toronto
    0.87
     сча
    0.79
    webkit
    0.79
     FaceTime
    0.78
     JavaScript
    0.78
    Sask
    0.77
     failing
    0.76
    Activations Density 0.020%

    No Known Activations