© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 719
    Prev
    Next
    INDEX
    Explanations

    Android UI `ViewHolder`

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

    The neuron is primarily detecting Java type names and class‐declaration tokens (e.g. class names, RecyclerView, ViewHolder, imports).

    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
     rush
    -1.19
     rushing
    -0.98
     rushes
    -0.80
     RUSH
    -0.76
    čiť
    -0.75
    プラグ
    -0.74
     atlan
    -0.71
    ◇
    -0.71
     Rush
    -0.70
    IconButton
    -0.68
    POSITIVE LOGITS
    ViewHolder
    1.99
     holder
    1.81
     ViewHolder
    1.77
    holder
    1.76
     Holder
    1.71
    Holder
    1.63
     holders
    1.56
     views
    1.27
     view
    1.27
     Holders
    1.26
    Activations Density 0.047%

    No Known Activations