© 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. 34-GEMMASCOPE-RES-131K
    7. 32025
    Prev
    Next
    INDEX
    Explanations

    awaiting results or completion

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

    The neuron strongly activates on programming code tokens—e.g. comment markers, API calls, punctuation, and other syntax—thus identifying code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Lear
    -0.81
    mand
    -0.80
    濮
    -0.78
    INCREF
    -0.78
    vtk
    -0.77
    cible
    -0.75
    feest
    -0.75
    釧
    -0.74
     inequ
    -0.73
     Todes
    -0.73
    POSITIVE LOGITS
     result
    0.93
     get
    0.85
     then
    0.84
     wait
    0.79
     Result
    0.78
     cerrada
    0.77
    Result
    0.77
    result
    0.73
    結果
    0.72
    Await
    0.71
    Activations Density 0.007%

    No Known Activations