© 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. 36358
    Prev
    Next
    INDEX
    Explanations

    C++ header files `.h`

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

    This neuron detects C/C++ header‐file include lines, i.e. file names ending in “.h” in #include directives.

    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
     grilling
    -1.02
     superseded
    -0.97
     prépar
    -0.94
     témoins
    -0.93
    מונות
    -0.93
     responsabili
    -0.92
     spelen
    -0.90
    Thats
    -0.90
     Âu
    -0.89
    お値段
    -0.88
    POSITIVE LOGITS
     that
    1.02
    ȍ
    0.88
    )=\
    0.86
     those
    0.86
    Page
    0.85
     $\
    0.85
    нская
    0.84
     "..\..\..\
    0.84
    nhung
    0.83
    ૮
    0.82
    Activations Density 0.019%

    No Known Activations