© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117926
    Prev
    Next
    INDEX
    Explanations

    class and self definitions

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

    The neuron is triggered by Swift source‐code tokens (especially keywords like “protocol,” “var,” “lazy,” etc.) in 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
     Hei
    -0.73
    ߋ
    -0.72
     〈
    -0.72
    getAbsolutePath
    -0.70
    やはり
    -0.66
     gł
    -0.66
    zky
    -0.66
    ialmente
    -0.66
     Zoological
    -0.66
    不去
    -0.65
    POSITIVE LOGITS
    computed
    0.81
    ekw
    0.80
     COMPUT
    0.75
    ederal
    0.75
    ショナル
    0.74
     להשת
    0.73
     bedeckt
    0.73
     closures
    0.73
     élève
    0.72
    xnn
    0.71
    Activations Density 0.041%

    No Known Activations