© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119999
    Prev
    Next
    INDEX
    Explanations

    https and nginx configurations

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

    the term "HTTPS" or protocol-related terms in technical contexts, particularly in code and documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on technical class‐ or protocol‐style tokens written in uppercase or CamelCase—e.g. “JSONArray” or “HTTPS.”

    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
    1
    -2.66
     यदि
    -2.30
     اگر
    -2.30
    是
    -2.23
    место
    -2.23
    ༛
    -2.20
    します
    -2.17
    ꔹ
    -2.14
    K
    -2.11
     své
    -2.08
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵
    2.23
     vollständ
    2.16
    k
    2.08
    完美的
    2.05
    好不容易
    2.00
    ing
    2.00
     лучших
    1.97
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.96
    渽
    1.95
    合适的
    1.93
    Activations Density 0.012%

    No Known Activations