© 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. 68592
    Prev
    Next
    INDEX
    Explanations

    unicode_literals

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

    The neuron responds to code‐style identifiers—especially multiword names in CamelCase or other API/class/function names in source text.

    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
    .
    -2.03
     you
    -1.90
    ”,
    -1.89
     एवं
    -1.59
     &
    -1.56
    jadikan
    -1.54
    ”，
    -1.53
    However
    -1.51
    หน้าน
    -1.51
     same
    -1.46
    POSITIVE LOGITS
    Ⴈ
    1.83
    d
    1.83
    t
    1.73
     até
    1.72
    錀
    1.70
    我们就
    1.69
    笵
    1.69
    赑
    1.68
    ⩥
    1.65
     verurs
    1.64
    Activations Density 0.011%

    No Known Activations