© 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. 22-GEMMASCOPE-RES-131K
    7. 38863
    Prev
    Next
    INDEX
    Explanations

    hide, move, screen

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

    The neuron activates on code tokens that name UI state‐change actions (e.g. disable, scrolling, hide, show, labels).

    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
     kadang
    -0.93
    Também
    -0.87
    每一次
    -0.83
     Studier
    -0.83
    Pacote
    -0.82
     sore
    -0.80
    相同
    -0.80
    Sometimes
    -0.79
    Possui
    -0.79
    vás
    -0.78
    POSITIVE LOGITS
     οι
    0.94
    ᑌ
    0.93
    portun
    0.89
    potion
    0.89
    нные
    0.88
     цвет
    0.88
    鬚
    0.88
    pronounced
    0.88
    thasone
    0.88
     项目
    0.87
    Activations Density 0.008%

    No Known Activations