© 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. 10-GEMMASCOPE-RES-131K
    7. 113217
    Prev
    Next
    INDEX
    Explanations

    navigation drawer or devise authentication

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

    the term "NavigationDrawer" or "Drawer" in Android UI code and documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires strongly on mentions of the Android “Navigation Drawer” UI component (and closely related terms like DrawerLayout).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    0
    -1.84
    y
    -1.68
    .”
    -1.60
    x
    -1.52
    S
    -1.49
    ,"
    -1.47
    we
    -1.46
    ob
    -1.42
    E
    -1.41
    o
    -1.41
    POSITIVE LOGITS
    schwar
    1.77
    camiseta
    1.77
     armas
    1.73
     victorias
    1.66
     suas
    1.66
     bosque
    1.61
    krok
    1.60
     momentos
    1.57
     colabor
    1.56
     habile
    1.56
    Activations Density 0.006%

    No Known Activations