© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    Flask web framework context

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

    the word "Flask" (the Python web framework).

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

    The neuron activates on any occurrence of the token “Flask” (or “flask”), i.e. references to the Flask web-framework.

    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
    
    -3.52
    潆
    -3.52
    賒
    -3.11
    퐸
    -2.98
    葑
    -2.97
    囖
    -2.97
    癀
    -2.94
    擼
    -2.92
    遹
    -2.89
     unſ
    -2.88
    POSITIVE LOGITS
    .
    3.45
    C
    3.44
    F
    3.41
    (
    3.27
    e
    3.23
    i
    3.06
    S
    2.97
    5
    2.77
     '
    2.70
    P
    2.70
    Activations Density 0.002%

    No Known Activations