© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90638
    Prev
    Next
    INDEX
    Explanations

    listing files and paths

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

    The neuron activates on programming‐language code snippets—identifying lines of source code (keywords, variable names, and syntax).

    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
    ⌜
    -0.76
    btnBack
    -0.75
     hasattr
    -0.72
    Unk
    -0.71
     barbed
    -0.71
    IZACIÓN
    -0.71
    を開催
    -0.70
    vie
    -0.69
    Симпто
    -0.69
    ране
    -0.69
    POSITIVE LOGITS
     glob
    1.46
    glob
    1.23
     sorted
    1.13
    sorted
    1.03
    listdir
    0.99
     natural
    0.85
    Sorted
    0.81
     next
    0.81
     Wild
    0.76
     есте
    0.76
    Activations Density 0.011%

    No Known Activations