© 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. 38334
    Prev
    Next
    INDEX
    Explanations

    android visibility or gone state

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

    This neuron spotlights Android XML layout structure tokens—especially references to ConstraintLayout and related tags.

    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
    logr
    -0.83
     może
    -0.81
    béco
    -0.77
    Nassau
    -0.71
     oiseaux
    -0.70
    ']))
    -0.69
    ernalia
    -0.68
     CGSize
    -0.68
    Nguyen
    -0.68
    лә
    -0.68
    POSITIVE LOGITS
     GONE
    1.45
     Gone
    1.43
     gone
    1.42
    Gone
    1.38
     visibility
    1.14
    gone
    1.09
    GONE
    1.02
    VISIBLE
    1.01
    Visibility
    1.00
     invisible
    0.98
    Activations Density 0.048%

    No Known Activations