© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127653
    Prev
    Next
    INDEX
    Explanations

    This neuron spots mentions of interactive UI elements or controls (e.g. tables, headers, buttons, tabs, text labels) in code or questions.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    click on element

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     according
    -1.08
     also
    -1.07
     as
    -0.91
     and
    -0.88
     for
    -0.88
    ,
    -0.85
     because
    -0.85
     with
    -0.85
     best
    -0.84
     since
    -0.84
    POSITIVE LOGITS
     Bereiche
    0.99
     itself
    0.99
    ʀ
    0.98
     musicale
    0.97
    itself
    0.95
     PyLong
    0.94
     moelle
    0.91
     accepts
    0.91
    jaran
    0.90
    どちら
    0.90
    Activations Density 0.051%

    No Known Activations