© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73483
    Prev
    Next
    INDEX
    Explanations

    C/C++ include statements

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

    The neuron detects C/C++ #include statements that reference “.h” header files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    𖤣
    -2.09
    着一
    -1.99
    了不少
    -1.98
    The
    -1.94
    着一个
    -1.85
     heartfelt
    -1.84
    WithMany
    -1.84
    了些
    -1.83
     К
    -1.82
    were
    -1.79
    POSITIVE LOGITS
     that
    2.42
     and
    2.03
    他
    1.91
     him
    1.83
    ?]
    1.77
     einzigartigen
    1.71
    verlust
    1.68
     of
    1.68
    seitige
    1.64
    经常
    1.62
    Activations Density 0.027%

    No Known Activations