© 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. 10-GEMMASCOPE-RES-131K
    7. 60720
    Prev
    Next
    INDEX
    Explanations

    git pull or pull request

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

    This neuron activates on the word “pull” (as in pull requests, git pull commands, PullCursor, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -2.56
    In
    -2.55
     \
    -2.53
     {
    -2.45
    ir
    -2.33
    )
    -2.25
     один
    -2.20
     t
    -2.17
     w
    -2.11
    .
    -2.09
    POSITIVE LOGITS
    felpa
    2.44
    痈
    2.39
    扨
    2.38
     recaudación
    2.38
     équipé
    2.36
    澌
    2.34
    淠
    2.31
     épaules
    2.28
     Corintios
    2.28
    oughby
    2.27
    Activations Density 0.009%

    No Known Activations