© 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. 22-GEMMASCOPE-RES-131K
    7. 13759
    Prev
    Next
    INDEX
    Explanations

    tabs and tab bodies

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

    This neuron detects occurrences of the token “tab” (and its variants like “tabs,” “tabControl,” or “tabPage”) in code or technical contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     a
    -1.05
    дал
    -1.04
    rights
    -1.00
    ernacle
    -0.99
    </strong>
    -0.98
    <0xDB>
    -0.98
    ’,
    -0.96
    ',
    -0.96
    ”,
    -0.93
    fourths
    -0.91
    POSITIVE LOGITS
    ủng
    1.15
    𝒙
    1.11
    पि
    1.09
     zwi
    1.09
    Содержание
    1.09
     nouve
    1.08
     vedno
    1.08
     Immigrants
    1.05
     ?>
    1.05
    ualitas
    1.05
    Activations Density 0.016%

    No Known Activations