© 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. 38761
    Prev
    Next
    INDEX
    Explanations

    javascript code keywords

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

    The neuron strongly responds to long runs of whitespace (indentation) at the start of code lines.

    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
     zowel
    -1.77
    摆手
    -1.76
    Butyl
    -1.75
    nicas
    -1.68
     证书
    -1.60
    tiac
    -1.58
    diyah
    -1.57
     But
    -1.57
     was
    -1.55
     terwijl
    -1.55
    POSITIVE LOGITS
    5
    2.16
    4
    2.14
    _
    2.13
    7
    2.00
    re
    2.00
    6
    2.00
    name
    1.89
    s
    1.88
    2
    1.86
    te
    1.78
    Activations Density 0.122%

    No Known Activations