© 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. 75277
    Prev
    Next
    INDEX
    Explanations

    XML/C# documentation comments

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

    The neuron is keyed to XML‐style documentation comment markers and content (e.g. the `<summary>` tags and their associated comment text).

    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
    autorité
    -1.02
     χρήση
    -0.99
     repeated
    -0.98
     こちら
    -0.95
     repeating
    -0.91
     espet
    -0.88
     meras
    -0.87
     protes
    -0.87
     Gegenteil
    -0.86
     vài
    -0.85
    POSITIVE LOGITS
    یریت
    0.93
    .<
    0.90
     toiture
    0.88
    。<
    0.87
     &=
    0.86
    命中
    0.85
    翰
    0.84
     "_"
    0.82
     "_
    0.82
    nah
    0.81
    Activations Density 0.001%

    No Known Activations