© 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. 22-GEMMASCOPE-RES-131K
    7. 64275
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

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

    The neuron fires most strongly on literal constant values (e.g. numbers and booleans) in code.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    嫉
    -0.96
     Моск
    -0.96
     Kristus
    -0.94
     clás
    -0.91
     ffs
    -0.90
     ribuan
    -0.90
    Solicit
    -0.90
    andaan
    -0.89
     tragé
    -0.88
    惭
    -0.88
    POSITIVE LOGITS
     wunder
    1.05
     evidente
    0.99
    떄
    0.98
    私たちは
    0.95
     wouldn
    0.95
     redu
    0.95
     ansiedad
    0.93
     アイドル
    0.92
    複数
    0.91
    Quando
    0.88
    Activations Density 0.002%

    No Known Activations