© 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. 70669
    Prev
    Next
    INDEX
    Explanations

    java file imports or declarations

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

    The neuron activates on identifiers for file or stream I/O (e.g. FileOutputStream, InputStream, OutputStream, Files, Paths, PrintWriter, os, fstream).

    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
    Глава
    -1.09
    もうすぐ
    -1.02
     Diretto
    -0.97
    景点
    -0.95
     whatnot
    -0.93
    仕事の
    -0.93
     HFILL
    -0.92
    すみません
    -0.89
    onger
    -0.89
    accompanied
    -0.86
    POSITIVE LOGITS
    鶯
    0.91
    низу
    0.88
    行
    0.86
    ^
    0.84
     emphasis
    0.83
    urtles
    0.82
     сал
    0.82
     Erst
    0.80
     Christen
    0.80
     forder
    0.80
    Activations Density 0.000%

    No Known Activations