© 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. 32819
    Prev
    Next
    INDEX
    Explanations

    show/hide elements

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

    This neuron fires on code that shows, hides, or toggles the visibility of user‐interface elements (e.g. divs/buttons) via display/visibility calls.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     from
    -1.20
    </b>
    -0.87
    刷新
    -0.85
    тропо
    -0.82
     can
    -0.81
    ultimo
    -0.81
     Однако
    -0.81
    เช่น
    -0.80
     каждого
    -0.79
    最终
    -0.79
    POSITIVE LOGITS
    aset
    0.96
    𝒙
    0.92
     melaksanakan
    0.92
     berisi
    0.91
    ários
    0.90
     hide
    0.90
    ってしまった
    0.90
     contenir
    0.88
    content
    0.88
     boolean
    0.88
    Activations Density 0.008%

    No Known Activations