© 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. 128944
    Prev
    Next
    INDEX
    Explanations

    packages

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

    The neuron is triggered by occurrences of the word “packages” in file‐path or import‐path contexts (i.e. references to a “packages” directory).

    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
     一
    -2.58
     
    -2.55
     VERY
    -2.44
     و
    -2.39
     It
    -2.34
    '
    -2.33
     lauded
    -2.25
     ใน
    -2.22
    it
    -2.17
    1
    -2.16
    POSITIVE LOGITS
    囿
    3.00
    衕
    2.84
     heightened
    2.72
    d
    2.63
    끽
    2.48
    襤
    2.44
    packages
    2.33
     horrific
    2.27
    勠
    2.27
     fourteen
    2.22
    Activations Density 0.003%

    No Known Activations