© 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. 22-GEMMASCOPE-RES-131K
    4. 70431
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron strongly activates on code comment headers—especially copyright notices with years and related punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     funktioniert
    -1.34
    <strong>
    -1.34
    🪛
    -1.27
     your
    -1.26
     infographic
    -1.26
     microbiome
    -1.23
     Instagram
    -1.23
     Pinterest
    -1.23
     Facebook
    -1.22
     https
    -1.20
    POSITIVE LOGITS
    修为
    1.72
    丹药
    1.52
    めている
    1.43
    噱
    1.41
    estos
    1.41
     läßt
    1.38
     Эти
    1.34
     travail
    1.34
     hommage
    1.31
     chrétienne
    1.31
    Activations Density 0.664%

    No Known Activations