© 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. 63522
    Prev
    Next
    INDEX
    Explanations

    Android EditText

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

    The neuron fires on Android UI class identifiers—especially view and widget names (e.g. View, LayoutInflater, EditText) in import or code declarations.

    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
    ਨਾ
    -0.71
     tästä
    -0.68
     toimi
    -0.66
     magenta
    -0.65
    úa
    -0.64
    equ
    -0.64
    पित
    -0.64
    чивать
    -0.64
     éléments
    -0.64
    зовые
    -0.64
    POSITIVE LOGITS
     edit
    3.31
    edit
    2.86
     Edit
    2.70
    EditText
    2.59
    Edit
    2.58
     EditText
    2.45
     edits
    2.39
     EDIT
    2.33
    EDIT
    2.19
     editing
    2.09
    Activations Density 0.050%

    No Known Activations