© 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. 10-GEMMASCOPE-RES-131K
    7. 70905
    Prev
    Next
    INDEX
    Explanations

    android xml resource ids

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

    The neuron fires on Android XML resource references and identifiers—tokens like “@+id…”, “res/…”, R.styleable entries, and schema URIs.

    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
    笮
    -1.66
     huf
    -1.64
     sors
    -1.63
     mallorca
    -1.62
     qashqai
    -1.52
     maten
    -1.50
     cern
    -1.49
     vernac
    -1.48
    示意图
    -1.47
     tekno
    -1.46
    POSITIVE LOGITS
     Empieza
    1.73
    blich
    1.57
     powsta
    1.56
     artık
    1.55
    ЛИ
    1.55
    ència
    1.52
     such
    1.52
     is
    1.44
    JHEP
    1.42
                
    1.39
    Activations Density 0.005%

    No Known Activations