© 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. 22-GEMMASCOPE-RES-131K
    7. 33015
    Prev
    Next
    INDEX
    Explanations

    mobile games and apps

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

    The neuron detects technical platform‐ and device‐specific terms (e.g. mobile/OS names, Cocoa Touch, viewport/device settings, touch events).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     selectAll
    -0.98
    zę
    -0.96
     langs
    -0.95
    ns
    -0.93
    abetes
    -0.93
     netts
    -0.93
     parle
    -0.90
     actionTypes
    -0.89
    >−
    -0.89
     chas
    -0.88
    POSITIVE LOGITS
     mobile
    1.48
     app
    1.45
     Android
    1.31
    Android
    1.24
     móvil
    1.18
    pocket
    1.15
    ện
    1.14
     phone
    1.14
     cellular
    1.13
    📱
    1.12
    Activations Density 0.141%

    No Known Activations