© 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. 83786
    Prev
    Next
    INDEX
    Explanations

    options and choices

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

    This neuron detects mentions of user interface options or controls that are disabled or “greyed out.”

    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
    我们的
    -1.20
    ifiquement
    -1.12
    因为
    -1.12
     katholischen
    -1.10
    velocityY
    -1.09
    因為
    -1.09
    ఆ
    -1.07
    ության
    -1.04
    contoh
    -1.02
    isburg
    -1.02
    POSITIVE LOGITS
     options
    2.11
     option
    1.83
    option
    1.69
     under
    1.67
    options
    1.64
    Options
    1.51
     menu
    1.51
     menus
    1.34
     Options
    1.34
     choices
    1.30
    Activations Density 0.142%

    No Known Activations