© 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. 37860
    Prev
    Next
    INDEX
    Explanations

    code comments and identifiers

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

    The neuron activates on tokens inside source‐code comment lines (e.g. “//” comments and their content).

    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
    ınıza
    -1.02
    私たちは
    -1.00
    私が
    -0.99
    bezpiecz
    -0.98
     curieux
    -0.98
    先週
    -0.98
     pomys
    -0.96
    ınızı
    -0.96
    Много
    -0.95
    私たちの
    -0.94
    POSITIVE LOGITS
     returns
    0.91
     implements
    0.88
     Satis
    0.88
    panic
    0.88
    g
    0.84
      
    0.83
     satisfied
    0.82
    8
    0.82
    TODO
    0.82
    DOF
    0.81
    Activations Density 0.090%

    No Known Activations