© 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. 34-GEMMASCOPE-RES-131K
    7. 32440
    Prev
    Next
    INDEX
    Explanations

    application server and windows

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

    The neuron is strongly triggered by mentions of the word “application.”

    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
     Drei
    -0.90
     Fünf
    -0.81
    之地
    -0.80
    無い
    -0.77
     verdadeiro
    -0.77
     announced
    -0.77
     office
    -0.75
     verschw
    -0.75
     devices
    -0.74
     blended
    -0.74
    POSITIVE LOGITS
     application
    1.15
     приложение
    1.13
     ứng
    1.09
     DEVELOPMENT
    1.07
     приложения
    1.07
    application
    1.05
     aplicación
    1.05
     development
    1.05
     aplikacji
    1.00
     getApplication
    0.99
    Activations Density 0.063%

    No Known Activations