© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11807
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron identifies copyright/license boilerplate lines, especially the “Copyright (c) YEAR” 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
     two
    -1.08
     three
    -0.96
     úspě
    -0.94
     one
    -0.94
     miesią
    -0.89
     during
    -0.88
     significant
    -0.88
    hskip
    -0.86
     concurso
    -0.86
    ਫ
    -0.85
    POSITIVE LOGITS
     IBM
    1.09
     Microsoft
    1.07
     volon
    0.98
     поиск
    0.97
     Gallimard
    0.94
    년
    0.93
    olverine
    0.92
    }<\
    0.90
    ţe
    0.90
     PagesJaunes
    0.90
    Activations Density 0.303%

    No Known Activations