© 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. 34-GEMMASCOPE-RES-131K
    7. 118348
    Prev
    Next
    INDEX
    Explanations

    C++ stream input/output operators

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

    The neuron is activated by C++ standard I/O constructs (cin, cout, iostream, endl, and related stream operators).

    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
    fgets
    -1.02
     чехол
    -0.91
    لیت
    -0.85
     fortsetter
    -0.79
     aligns
    -0.77
    <-
    -0.76
     signo
    -0.74
     salonu
    -0.74
    ട
    -0.74
     subsequently
    -0.73
    POSITIVE LOGITS
     >>
    2.22
    >>
    1.65
     $>$
    1.05
    )>>
    1.03
     cin
    0.87
    ikkert
    0.85
    }>\
    0.85
    ">>
    0.82
     ?>>
    0.82
    Juventus
    0.79
    Activations Density 0.001%

    No Known Activations