© 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. 114077
    Prev
    Next
    INDEX
    Explanations

    stack trace

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

    stack traces and error messages in programming contexts.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5

    The neuron fires on elements of stack‐trace lines (e.g. the “at” entries, back‐trace markers, and line‐number tokens) indicating it’s detecting exception stack frame information.

    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
    炻
    -1.15
     Cinnamon
    -1.14
    сіб
    -1.13
     stadt
    -1.12
     اور
    -1.10
     agrícola
    -1.10
     feststellen
    -1.09
    灩
    -1.09
    ⃣
    -1.09
     huo
    -1.09
    POSITIVE LOGITS
    黑衣
    1.39
    inescence
    1.22
     you
    1.20
    諡
    1.18
     fameux
    1.18
    maría
    1.15
    yatı
    1.15
    РС
    1.14
    dropIfExists
    1.14
     estos
    1.14
    Activations Density 0.082%

    No Known Activations