© 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. 50395
    Prev
    Next
    INDEX
    Explanations

    tabs or tab

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

    The neuron is strongly triggered by any mention of “tab” (e.g. “tabs”, “tabbed”, “TabControl”)—i.e. references to tab‐based UI components or navigation.

    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
    assion
    -0.90
    iration
    -0.81
     tono
    -0.80
    𝑮
    -0.80
    territ
    -0.79
    Plum
    -0.79
    gebnis
    -0.78
    erik
    -0.76
    UEGO
    -0.76
    ยะ
    -0.75
    POSITIVE LOGITS
     tabs
    2.30
     tab
    2.27
    Tab
    2.09
     Tab
    1.91
    tab
    1.89
    tabs
    1.85
     Tabs
    1.80
    Tabs
    1.76
    TAB
    1.47
     TAB
    1.45
    Activations Density 0.052%

    No Known Activations