© 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. 22-GEMMASCOPE-RES-131K
    7. 13763
    Prev
    Next
    INDEX
    Explanations

    findViewById and xml

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

    The neuron is detecting integer resource ID literals in Android view‐lookup calls (e.g. the numeric IDs in “(ViewType)1234 findViewById(…)”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    そして
    -1.20
     cartaz
    -1.20
    และ
    -1.18
    8
    -1.14
     to
    -1.14
    以及
    -1.09
     estadia
    -1.09
    7
    -1.05
     consentimento
    -1.05
    3
    -1.05
    POSITIVE LOGITS
     in
    1.27
     vanske
    1.25
     påvir
    1.23
     señores
    1.20
     anillos
    1.20
    هرست
    1.20
     españolas
    1.19
     requerimientos
    1.18
     található
    1.16
     långt
    1.16
    Activations Density 0.001%

    No Known Activations