© 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. 38624
    Prev
    Next
    INDEX
    Explanations

    github blob/master paths

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

    The neuron strongly activates on the “/blob/master/” segment of GitHub/GitLab URLs, i.e. it detects links to specific files in code repositories.

    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
    增加
    -0.84
    西方
    -0.80
    総
    -0.74
    楼
    -0.74
     legg
    -0.73
    awar
    -0.73
    стит
    -0.73
    ened
    -0.72
     جمهور
    -0.72
    单
    -0.72
    POSITIVE LOGITS
     master
    1.20
     Masters
    1.12
    Master
    1.00
     MASTER
    0.98
     Master
    0.93
    何回
    0.90
     masters
    0.88
    master
    0.82
    Masters
    0.82
     absolue
    0.80
    Activations Density 0.007%

    No Known Activations