© 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. 97890
    Prev
    Next
    INDEX
    Explanations

    navigation components

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

    The neuron fires on mentions of Android’s Navigation Drawer (and related navigation UI component) terms in code.

    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
     Shoulders
    -0.77
    pto
    -0.77
     Camar
    -0.73
     [];
    -0.73
    sikker
    -0.73
     setMessage
    -0.71
    moet
    -0.71
    Disk
    -0.71
    mesas
    -0.70
     desejo
    -0.70
    POSITIVE LOGITS
     nav
    1.03
    NavController
    0.93
     androidx
    0.91
    ViewModels
    0.91
     NavController
    0.90
    चर
    0.90
    Рис
    0.87
     host
    0.83
    nav
    0.80
    支持
    0.80
    Activations Density 0.004%

    No Known Activations