© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49603
    Prev
    Next
    INDEX
    Explanations

    header file inclusions

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

    The neuron activates on tokens that are part of C/C++ include file paths—i.e. library and header names in “#include” statements.

    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
     most
    -0.98
     notable
    -0.88
     with
    -0.85
    UALLY
    -0.84
     obvious
    -0.82
    ;
    -0.81
     Zubehör
    -0.77
    newswire
    -0.77
     usually
    -0.77
     from
    -0.77
    POSITIVE LOGITS
    hpp
    1.17
     header
    1.16
    h
    1.08
     INCLUDED
    1.03
     CONTIN
    0.93
    aughn
    0.91
    ساعت
    0.91
     Ман
    0.91
    ersatz
    0.90
    一方面
    0.90
    Activations Density 0.112%

    No Known Activations