© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48425
    Prev
    Next
    INDEX
    Explanations

    mobile apps and commerce

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

    The neuron strongly activates on the term “mobile” (including “m-commerce” and related mobile-specific tokens).

    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
    argentina
    -0.94
    Podcasts
    -0.93
     lauded
    -0.91
    pompa
    -0.91
    かっこいい
    -0.86
     stück
    -0.85
    nvm
    -0.85
    流石
    -0.84
    Plateau
    -0.84
     montagnes
    -0.83
    POSITIVE LOGITS
     devices
    1.45
     app
    1.41
     device
    1.31
     apps
    1.16
     first
    1.15
    devices
    1.14
    friendly
    1.13
    应用程序
    1.10
    📱
    1.09
    Device
    1.08
    Activations Density 0.032%

    No Known Activations