© 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. 73517
    Prev
    Next
    INDEX
    Explanations

    Q: followed by question

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

    The neuron activates on programming‐language syntax tokens (like keywords, decorators, file‐format extensions, etc.), effectively spotting code fragments.

    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
     liksom
    -0.81
    amkeit
    -0.79
     krijgen
    -0.76
    кономі
    -0.74
    ところで
    -0.73
    Problems
    -0.73
     "---
    -0.73
    يقة
    -0.73
    قي
    -0.72
    bola
    -0.72
    POSITIVE LOGITS
     durante
    0.92
    谐
    0.90
    Durante
    0.84
     xrange
    0.80
    วน
    0.80
    ordenadas
    0.80
    INSTRUCTION
    0.79
     symmetry
    0.77
     limelight
    0.77
     handelt
    0.76
    Activations Density 0.000%

    No Known Activations