© 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. 6893
    Prev
    Next
    INDEX
    Explanations

    programming helper modules

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

    This neuron detects occurrences of the identifier “Helper” (i.e. code tokens ending in “Helper,” such as class or file names).

    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
    '
    -3.17
     mayoría
    -2.55
     suaves
    -2.50
    幼稚
    -2.36
    ↵
    -2.30
    剮
    -2.25
    の歴史
    -2.23
     juzg
    -2.22
    AddTagHelper
    -2.19
    新手
    -2.19
    POSITIVE LOGITS
    0
    3.45
    7
    3.14
     However
    2.91
    5
    2.81
    けれ
    2.77
     Therefore
    2.73
     According
    2.73
     télévis
    2.70
    Because
    2.64
    也沒
    2.64
    Activations Density 0.005%

    No Known Activations