© 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. 45707
    Prev
    Next
    INDEX
    Explanations

    Google App Engine

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

    The neuron activates on explicit mentions of the “Google App Engine” platform (including its associated version/runtime context).

    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
    kým
    -0.89
    masalah
    -0.79
     conduct
    -0.74
    stery
    -0.71
    дцать
    -0.71
     ganadores
    -0.70
    psia
    -0.69
     пове
    -0.69
     spé
    -0.68
    зор
    -0.68
    POSITIVE LOGITS
    HEADER
    0.77
    environment
    0.77
     fairs
    0.75
    fwrite
    0.74
     Environment
    0.71
    fractive
    0.71
     flex
    0.71
     Chronicles
    0.69
    pgfmath
    0.69
     header
    0.69
    Activations Density 0.012%

    No Known Activations