© 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. 22-GEMMASCOPE-RES-131K
    7. 68930
    Prev
    Next
    INDEX
    Explanations

    generated by tool

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

    The neuron detects boilerplate comments indicating that code was automatically generated by a tool.

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

    No Comments

    Negative Logits
     its
    -1.16
     щодо
    -1.16
    好久
    -1.12
     their
    -1.06
    OfWork
    -1.04
    第六
    -1.04
    chemise
    -1.03
    seguridad
    -1.03
     réus
    -1.02
    状態で
    -1.02
    POSITIVE LOGITS
     шпи
    1.05
     одним
    1.05
    では
    0.99
    arrhea
    0.96
    ensical
    0.96
    lare
    0.94
     berichten
    0.94
    มาะ
    0.93
    mability
    0.92
    下意识
    0.91
    Activations Density 0.018%

    No Known Activations