© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73292
    Prev
    Next
    INDEX
    Explanations

    pip install command

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

    The neuron detects occurrences of “pip” (especially in pip install commands) in code or text.

    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
    ⽌
    -2.72
     användas
    -2.55
     Bedürfn
    -2.55
     to
    -2.52
     individuellen
    -2.50
     ด้วย
    -2.45
     come
    -2.38
     unangemess
    -2.36
     pokud
    -2.30
    .
    -2.27
    POSITIVE LOGITS
     είναι
    3.02
    From
    2.80
    ꯶
    2.78
    -"
    2.50
    How
    2.50
     guadag
    2.48
    都沒有
    2.47
     护
    2.45
     ומ
    2.42
    ním
    2.34
    Activations Density 0.005%

    No Known Activations