© 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. 72064
    Prev
    Next
    INDEX
    Explanations

    nested code and data structures

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

    The neuron fires primarily on occurrences of the word “nested” (and closely related terms like “recursive”) in code or technical contexts.

    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
    嘥
    -3.31
    犼
    -2.64
    ⡦
    -2.58
    廰
    -2.52
     mesmas
    -2.52
    螻
    -2.48
    馓
    -2.47
    搋
    -2.42
    瓩
    -2.42
    鸸
    -2.39
    POSITIVE LOGITS
    after
    2.89
    s
    2.77
    with
    2.69
    as
    2.58
    because
    2.56
     semua
    2.55
     all
    2.52
    b
    2.50
     nuanced
    2.47
     để
    2.42
    Activations Density 0.003%

    No Known Activations