© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69220
    Prev
    Next
    INDEX
    Explanations

    gen followed by code artifacts

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

    This neuron detects occurrences of the token “gen” (often followed by numbers) in code files—i.e. markers of auto-generated code.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     They
    -3.20
    </strong>
    -2.66
    )”
    -2.34
     jie
    -2.30
     ";
    -2.25
    鐿
    -2.23
    …”
    -2.22
    管道
    -2.19
    “.
    -2.17
    場合は
    -2.17
    POSITIVE LOGITS
     ''
    2.70
     exodus
    2.44
    "
    2.41
     recientes
    2.34
     uproar
    2.27
    '
    2.27
     –
    2.16
    gen
    2.16
    孖
    2.14
    ;
    2.13
    Activations Density 0.005%

    No Known Activations