© 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. 70281
    Prev
    Next
    INDEX
    Explanations

    dull, dim, faded, greyed out

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

    The neuron detects mentions of UI controls or options being 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
    蓝色
    -0.78
     Maple
    -0.74
    tacle
    -0.74
     maple
    -0.73
     Bilder
    -0.73
    ampling
    -0.73
     Medicare
    -0.71
    maple
    -0.71
     Puri
    -0.71
    狭い
    -0.71
    POSITIVE LOGITS
     dull
    2.91
     dim
    2.63
     faded
    2.56
     dimmer
    2.52
     dimmed
    2.38
    dim
    2.28
     faint
    2.23
     dimming
    2.17
     fade
    2.14
     Dull
    2.11
    Activations Density 0.065%

    No Known Activations