© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119005
    Prev
    Next
    INDEX
    Explanations

    menu bar

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

    The neuron detects mentions of menu‐bar (the word “menu” followed by “bar”) in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     menetapkan
    -0.89
    Eksterne
    -0.87
    ovací
    -0.79
    mocha
    -0.75
     membunuh
    -0.75
     mengingatkan
    -0.73
     الاحتلال
    -0.73
     erkennt
    -0.72
     hypertension
    -0.72
    findpost
    -0.72
    POSITIVE LOGITS
     menu
    1.61
    JMenuBar
    1.61
     men
    1.60
    MenuBar
    1.56
     MEN
    1.38
     menus
    1.37
    menuStrip
    1.35
    menubar
    1.34
     Men
    1.32
     Menu
    1.23
    Activations Density 0.012%

    No Known Activations