© 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. 22-GEMMASCOPE-RES-131K
    4. 79881
    Prev
    Next
    INDEX
    Explanations

    `@Override` in code

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

    The neuron activates on the Java @Override annotation, i.e. it detects overridden‐method declarations.

    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
     PUSTAKA
    -1.84
    archivi
    -1.60
    astricht
    -1.50
    इटम
    -1.48
     pilih
    -1.38
    หรือ
    -1.35
     וכן
    -1.34
    
    -1.32
    我们的
    -1.32
    และ
    -1.32
    POSITIVE LOGITS
    ↵
    2.23
    ,
    1.93
    ,”
    1.47
    p
    1.45
    u
    1.41
     哪些
    1.38
    :</
    1.38
    '
    1.33
     olduğ
    1.31
     –
    1.30
    Activations Density 0.002%

    No Known Activations