© 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. 22-GEMMASCOPE-RES-131K
    7. 129747
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on words and fragments from software licensing and copyright-disclaimer boilerplate.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    software licenses and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     on
    -2.56
     in
    -2.25
     by
    -2.11
     from
    -2.11
     at
    -1.85
     even
    -1.73
     all
    -1.68
     with
    -1.63
     through
    -1.62
     for
    -1.60
    POSITIVE LOGITS
     diversos
    1.55
    Симпто
    1.45
    ولايات
    1.40
     développer
    1.34
     カジュアル
    1.31
    ウェット
    1.30
     gérer
    1.27
     outburst
    1.27
     faciliter
    1.27
     colorear
    1.25
    Activations Density 0.083%

    No Known Activations