© 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. 1590
    Prev
    Next
    INDEX
    Explanations

    copyright and include headers

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

    The neuron is primarily detecting C/C++ preprocessor include directives and their quoted or angled header file paths.

    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
     Ahead
    -0.81
    ↰
    -0.74
    onReady
    -0.73
     Amphi
    -0.71
     Occupation
    -0.70
    reiches
    -0.69
     mythical
    -0.69
    Occupation
    -0.69
    気に入りの
    -0.68
     Ports
    -0.68
    POSITIVE LOGITS
     encoding
    0.83
    ocide
    0.80
     thủ
    0.79
    encoding
    0.78
    azioni
    0.77
     kelle
    0.76
     taki
    0.75
    Charset
    0.75
    țial
    0.74
     chart
    0.73
    Activations Density 0.002%

    No Known Activations