© 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. 84314
    Prev
    Next
    INDEX
    Explanations

    C++ include directives

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

    The neuron fires on quoted filename strings 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
     dieselbe
    -0.89
    bumptech
    -0.87
    vskip
    -0.86
    
    -0.82
    Limiter
    -0.82
     vă
    -0.81
    γρά
    -0.81
    這種
    -0.81
     terremoto
    -0.80
     servlet
    -0.79
    POSITIVE LOGITS
    headers
    1.37
     header
    1.30
    include
    1.30
    Header
    1.21
     include
    1.16
     Header
    1.12
     headers
    1.12
    header
    1.08
    includes
    1.07
    Include
    1.07
    Activations Density 0.122%

    No Known Activations