© 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. 116579
    Prev
    Next
    INDEX
    Explanations

    App settings and configurations

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

    The neuron fires on mentions of an IIS/ASP .NET Application Pool (e.g. “Application Pool,” “Default App Pool,” “app pool”).

    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
     Forbes
    -0.78
    斂
    -0.68
    omatous
    -0.68
    ôi
    -0.66
    邪魔
    -0.64
     فور
    -0.64
    annels
    -0.63
     connessione
    -0.63
     PHP
    -0.62
    Произ
    -0.62
    POSITIVE LOGITS
    DbContext
    1.08
     Cousin
    0.84
    ཞ
    0.81
    šné
    0.78
    iclo
    0.74
     Oll
    0.73
     泥
    0.71
     предлагает
    0.71
    sqr
    0.71
    پزخانه
    0.70
    Activations Density 0.041%

    No Known Activations