© 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. 22-GEMMASCOPE-RES-131K
    7. 34616
    Prev
    Next
    INDEX
    Explanations

    programming, git, code snippets

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

    The neuron activates on version‐control jargon—especially Git commands and repo/branch references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     holand
    -1.63
     farbe
    -1.63
    𖡼
    -1.53
     biela
    -1.52
    latimes
    -1.52
     histó
    -1.52
    ⸎
    -1.50
    ݯ
    -1.49
    のイメージ
    -1.48
    ⛦
    -1.48
    POSITIVE LOGITS
    M
    1.48
    s
    1.38
    R
    1.37
    讴
    1.34
    to
    1.33
    D
    1.32
    F
    1.30
    U
    1.27
    H
    1.27
    N
    1.23
    Activations Density 0.038%

    No Known Activations