© 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. 103726
    Prev
    Next
    INDEX
    Explanations

    C++ cout statement

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

    The neuron flags C++ iostream stream‐IO tokens (e.g. “cout,” “endl,” “cin” and related fragments).

    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
    توضیحات
    -0.81
    )+
    -0.79
     ağı
    -0.79
     parç
    -0.79
    nesty
    -0.78
    fallout
    -0.77
    <0xE4>
    -0.77
    celtic
    -0.77
     gás
    -0.76
     season
    -0.75
    POSITIVE LOGITS
     <<
    3.03
    <<
    1.91
    ]<<
    1.43
    ()<<
    1.41
    endl
    1.41
    )<<
    1.41
    "<<
    1.38
     shall
    1.37
    <<"
    1.33
     endl
    1.27
    Activations Density 0.004%

    No Known Activations