© 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. 22-GEMMASCOPE-RES-131K
    7. 66486
    Prev
    Next
    INDEX
    Explanations

    Q: or Reader question:

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

    This neuron detects XML-style documentation comment markers (lines beginning with “///”) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.48
    mitsub
    -1.37
    hyundai
    -1.29
     agricultores
    -1.27
    mazda
    -1.27
    mizuno
    -1.23
    carian
    -1.20
    dekor
    -1.15
     fuma
    -1.13
    tidos
    -1.13
    POSITIVE LOGITS
    1.43
    m
    1.30
    u
    1.27
    k
    1.27
    h
    1.24
    </em>
    1.24
    j
    1.23
    A
    1.23
    o
    1.23
    e
    1.23
    Activations Density 0.000%

    No Known Activations