© 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. 84750
    Prev
    Next
    INDEX
    Explanations

    explaining necessity or fixes

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

    This neuron detects tokens that appear inside code comments (e.g. JSDoc, CSS or inline “//”/“/*…*/” comment blocks).

    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
     your
    -1.56
    あなたの
    -1.30
     and
    -1.25
    ρούν
    -1.21
    sätzlich
    -1.13
    offrir
    -1.13
    accompag
    -1.10
     広場
    -1.09
    あなたが
    -1.09
     ។
    -1.07
    POSITIVE LOGITS
     because
    2.08
     we
    1.91
     avoid
    1.71
     here
    1.70
     sometimes
    1.63
     due
    1.62
     since
    1.55
     ensure
    1.45
     чтобы
    1.39
    because
    1.38
    Activations Density 0.097%

    No Known Activations