© 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. 10-GEMMASCOPE-RES-131K
    7. 127285
    Prev
    Next
    INDEX
    Explanations

    Microsoft Word, Illustrator, Access

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

    The main thing this neuron does is detect mentions of Microsoft Office (and related) application names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     in
    -1.68
     ‘
    -1.58
     onPostExecute
    -1.56
     Tahun
    -1.41
     hver
    -1.40
     спор
    -1.39
     —
    -1.38
     This
    -1.37
     that
    -1.36
     dasar
    -1.34
    POSITIVE LOGITS
    呖
    1.73
     estadía
    1.66
    饜
    1.64
     automó
    1.55
     câmbio
    1.49
    帔
    1.49
     dança
    1.48
    還會
    1.47
     trabalhar
    1.46
     senhora
    1.45
    Activations Density 0.056%

    No Known Activations