© 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. 98676
    Prev
    Next
    INDEX
    Explanations

    error and status codes

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

    The neuron activates on standalone numeric tokens (e.g. error‐ or exit‐code numbers and other digit sequences).

    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
    ;
    -1.48
    </h3>
    -1.46
     bundes
    -1.44
     for
    -1.43
     with
    -1.42
     his
    -1.39
    上述
    -1.37
    。
    -1.35
     those
    -1.30
    f
    -1.30
    POSITIVE LOGITS
    𓋼
    1.70
    GGLE
    1.66
    }$,
    1.63
    ꙰
    1.62
    indest
    1.61
    URRED
    1.59
     másik
    1.58
    ごめんなさい
    1.56
     passenden
    1.56
    та
    1.56
    Activations Density 0.008%

    No Known Activations