© 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. 22-GEMMASCOPE-RES-131K
    7. 65433
    Prev
    Next
    INDEX
    Explanations

    Android/Java code and questions

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

    The main thing this neuron does is detect references to Android UI view classes (e.g. LayoutInflater, View, ViewGroup) in code.

    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
     all
    -0.94
    子は
    -0.90
     as
    -0.89
     each
    -0.89
    cheri
    -0.88
    ！（
    -0.86
    (""+
    -0.85
     choisissez
    -0.85
    じた
    -0.84
     answer
    -0.84
    POSITIVE LOGITS
    Faktor
    1.00
    きれい
    0.96
    Opin
    0.92
    ことも
    0.92
    Krank
    0.92
    色んな
    0.91
    Ruj
    0.88
    Mvh
    0.87
    Artigo
    0.87
    outil
    0.86
    Activations Density 0.001%

    No Known Activations