© 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. 84721
    Prev
    Next
    INDEX
    Explanations

    paths and scientific terms

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

    This neuron detects Go import path strings (quoted module/package paths) in source code.

    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
    isPrime
    -0.81
    懈
    -0.81
    một
    -0.80
     sucker
    -0.75
     lined
    -0.75
     requ
    -0.75
    ąp
    -0.75
     mek
    -0.74
     spoiling
    -0.73
     Tem
    -0.72
    POSITIVE LOGITS
     skupina
    0.77
    engk
    0.73
     optar
    0.73
    蚝
    0.71
    ankind
    0.71
     partiellement
    0.70
     narci
    0.69
    pagnole
    0.69
    logii
    0.69
    яз
    0.68
    Activations Density 0.012%

    No Known Activations