© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101344
    Prev
    Next
    INDEX
    Explanations

    UI actions and toolbars

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

    HTML/code attributes and programming interface elements like "actions", "toolbar", and "options".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on UI‐related control labels—especially “Actions,” “Toolbar,” “tools,” and similar section or button group headings.

    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
    .
    -1.47
     that
    -1.45
     our
    -1.44
     rígido
    -1.44
     vanskelig
    -1.38
    '
    -1.38
     your
    -1.34
    )
    -1.32
     especially
    -1.31
     many
    -1.30
    POSITIVE LOGITS
    芣
    1.57
    eczka
    1.49
     awakeFromNib
    1.45
     inox
    1.45
    ING
    1.44
    Istorija
    1.43
     ultime
    1.41
    ouage
    1.38
     facilite
    1.35
    nání
    1.34
    Activations Density 0.031%

    No Known Activations