© 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. 68149
    Prev
    Next
    INDEX
    Explanations

    list items and UI components

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

    The neuron detects mentions of Android list‐view components and their adapters (e.g. ListView, ArrayAdapter, ListActivity, simple_list_item).

    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
    鹪
    -1.55
    妡
    -1.52
    栳
    -1.45
     altavoz
    -1.43
    喁
    -1.38
    ったので
    -1.36
    栊
    -1.31
    有何
    -1.30
    Ꮵ
    -1.29
    蛱
    -1.27
    POSITIVE LOGITS
    1
    1.33
     if
    1.14
     açık
    1.10
     it
    1.04
    리를
    1.03
    »
    1.03
     inaccuracies
    1.02
    都
    0.99
     this
    0.98
     for
    0.94
    Activations Density 0.037%

    No Known Activations