© 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. 10-GEMMASCOPE-RES-131K
    7. 6880
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron responds to code‐style punctuation tokens—things like “[” brackets, “<” angle brackets, “/” slashes (as in URLs or imports), and similar symbols.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </i>
    -1.89
    -
    -1.71
    f
    -1.70
    c
    -1.55
    o
    -1.52
    '
    -1.47
    I
    -1.46
    u
    -1.45
     my
    -1.43
     ‘
    -1.42
    POSITIVE LOGITS
    圌
    1.72
    righted
    1.71
    hooter
    1.68
    takings
    1.67
     rezer
    1.67
    enance
    1.67
     และ
    1.67
    rages
    1.66
    thday
    1.65
    teries
    1.65
    Activations Density 0.001%

    No Known Activations