© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62566
    Prev
    Next
    INDEX
    Explanations

    analytics, Q&A, or lists

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

    The neuron strongly activates on programming‐language tokens and punctuation (e.g. code keywords, identifiers, braces, dots, semicolons), i.e. it detects code snippets.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Colón
    -0.78
     Luton
    -0.76
    fontaine
    -0.75
    phil
    -0.72
    inne
    -0.72
    تن
    -0.71
     progrès
    -0.68
    kowym
    -0.68
     contem
    -0.68
     inverter
    -0.68
    POSITIVE LOGITS
     events
    0.97
     visitor
    0.94
     visitors
    0.94
    Visitor
    0.92
     Visitor
    0.92
     marketer
    0.86
     collector
    0.86
     Adobe
    0.85
     Visitors
    0.84
    adobe
    0.84
    Activations Density 0.046%

    No Known Activations