© 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. 6932
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives or code comments

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

    The neuron fires on C/C++ preprocessor include lines, specifically recognizing header‐file names (e.g. “*.hpp”, “*.h”, etc.) 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_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
     for
    -1.37
     any
    -1.30
     their
    -1.23
     As
    -1.23
     in
    -1.22
     three
    -1.21
     from
    -1.21
     if
    -1.18
     with
    -1.17
     With
    -1.16
    POSITIVE LOGITS
     #
    2.48
    #
    2.33
     \#
    2.17
     $\#
    1.98
    ,#
    1.78
     '#
    1.77
    \#
    1.73
    ">#
    1.69
    +#
    1.66
    =#
    1.66
    Activations Density 0.097%

    No Known Activations