© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15266
    Prev
    Next
    INDEX
    Explanations

    UI component actions

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

    The neuron fires on names or labels of button controls (action words like “add,” “reset,” “search,” “download,” “get,” etc.) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     durante
    -1.90
     overly
    -1.89
     decidedly
    -1.79
     dando
    -1.77
     tumultuous
    -1.75
    nearly
    -1.74
     OVER
    -1.72
     OTHER
    -1.72
     startling
    -1.71
     bleak
    -1.71
    POSITIVE LOGITS
     for
    2.66
     because
    2.03
     років
    1.77
     this
    1.70
     after
    1.66
     from
    1.66
     through
    1.64
    懺
    1.58
     an
    1.55
     superbly
    1.55
    Activations Density 0.019%

    No Known Activations