© 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. 604
    Prev
    Next
    INDEX
    Explanations

    programming output

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

    The neuron fires on code tokens involved in output/printing calls (e.g. System.out.println, printf, echo, etc.).

    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
    ท่าน
    -1.02
    了一会儿
    -1.02
    その
    -1.01
    توضیحات
    -1.00
    ⅖
    -0.97
     통해
    -0.97
     PUSTAKA
    -0.96
     カーディガン
    -0.95
    Werdegang
    -0.94
     Krieges
    -0.94
    POSITIVE LOGITS
     first
    1.06
    cito
    0.96
     welcome
    0.94
     what
    0.94
    房地产
    0.93
     one
    0.91
    grafía
    0.90
    pr
    0.87
     inaugural
    0.87
     "
    0.86
    Activations Density 0.010%

    No Known Activations