© 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. 71687
    Prev
    Next
    INDEX
    Explanations

    xml documentation summaries

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

    The neuron specifically fires on XML documentation “summary” tags (i.e. the `<summary>` elements in code comments).

    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
    abbix
    -1.36
     يمكن
    -1.27
     ersten
    -1.27
    などの
    -1.23
     berbagai
    -1.23
     outras
    -1.20
    などで
    -1.16
    mbol
    -1.15
     bazı
    -1.14
    などに
    -1.14
    POSITIVE LOGITS
     greatly
    1.18
    P
    1.12
     does
    1.10
     jupe
    1.06
     always
    1.01
     substantially
    0.98
    ↵
    0.98
    J
    0.98
     epitom
    0.96
     américa
    0.94
    Activations Density 0.001%

    No Known Activations