© 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. 16755
    Prev
    Next
    INDEX
    Explanations

    update followed by context

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

    The neuron consistently activates on the token “update” (e.g. function or variable names containing “update”) in code or documentation.

    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
    }$
    -3.22
    ’
    -2.98
     '
    -2.89
    -2.66
     "
    -2.47
     ("
    -2.45
    ',
    -2.41
    and
    -2.41
    "
    -2.36
    \\
    -2.33
    POSITIVE LOGITS
    ஂ
    3.13
    ဴ
    2.81
    摃
    2.75
    鷓
    2.72
     แดง
    2.66
    諴
    2.61
    Ⲉ
    2.56
    इटम
    2.41
    还真是
    2.38
     ขาว
    2.38
    Activations Density 0.026%
    No Known Activations