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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6746
    Prev
    Next
    INDEX
    Explanations

    admin panel or section

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

    The neuron activates on mentions of administrative/configuration interfaces (e.g. “Admin section” or “control panel”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ester
    -0.76
     prestar
    -0.75
    crema
    -0.73
    kse
    -0.72
     Hibernate
    -0.72
    thum
    -0.72
    ッセ
    -0.72
    籍
    -0.71
    伤感
    -0.71
     lorsque
    -0.69
    POSITIVE LOGITS
     admin
    3.02
     panel
    2.84
     dashboard
    2.67
    admin
    2.56
    panel
    2.52
     Admin
    2.42
     Dashboard
    2.36
    Panel
    2.33
     Panel
    2.33
    Admin
    2.27
    Activations Density 0.088%

    No Known Activations