© 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. 37882
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron is tuned to spot code‐style tokens—especially Python keywords and import/coding directives—in a document.

    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
     Bep
    -0.71
    𝖇
    -0.70
     kuta
    -0.68
     знаем
    -0.67
     cooldown
    -0.67
    sedown
    -0.66
    phylactic
    -0.66
     ename
    -0.66
     vải
    -0.65
     mandibular
    -0.65
    POSITIVE LOGITS
     ru
    0.72
     גור
    0.71
    point
    0.71
     αν
    0.70
     absol
    0.70
     ta
    0.69
     pil
    0.69
     hr
    0.68
    ASSERT
    0.68
    inosi
    0.68
    Activations Density 0.046%

    No Known Activations