© 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. 98656
    Prev
    Next
    INDEX
    Explanations

    ) followed by {

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

    The neuron activates on Java method definitions (especially overridden callback methods marked with @Override and their signatures).

    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
     karena
    -1.12
     terjun
    -1.08
     supaya
    -1.05
     comentário
    -1.05
    Spesifikasi
    -1.00
    onResume
    -0.98
     siap
    -0.96
    5
    -0.96
     mídia
    -0.96
     cancelamento
    -0.95
    POSITIVE LOGITS
    主机
    0.94
     Oster
    0.89
     homens
    0.87
    zw
    0.86
     fighting
    0.85
    啟動
    0.85
     among
    0.84
     run
    0.84
    采用了
    0.84
    ↵
    0.84
    Activations Density 0.002%

    No Known Activations