© 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. 34988
    Prev
    Next
    INDEX
    Explanations

    menu and menu items

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

    The neuron strongly activates on programming‐related mentions of “menu” (e.g. menu creation or MenuItem code references).

    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
     Hermann
    -0.84
    Maximum
    -0.82
     Herbert
    -0.78
     Marshal
    -0.77
     Greg
    -0.75
     Marshall
    -0.74
    Herbert
    -0.71
    IkReal
    -0.71
    Greg
    -0.71
    JLabel
    -0.69
    POSITIVE LOGITS
    MenuItem
    2.59
     MenuItem
    2.44
     menu
    1.91
    menuItem
    1.84
     menuItem
    1.77
     item
    1.59
     JMenuItem
    1.50
    menu
    1.47
     Menu
    1.26
    メニュー
    1.22
    Activations Density 0.025%

    No Known Activations