© 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. 105423
    Prev
    Next
    INDEX
    Explanations

    open study or surgery

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

    research study terminology like "open study," "open-label," and other scientific research methodologies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on the phrase “open … study” (e.g. “open study,” “open prospective study,” “open-label study”), i.e. headings of open clinical studies.

    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
     I
    -1.31
     Thus
    -1.23
     cuando
    -1.22
    Explore
    -1.19
    应该
    -1.19
     about
    -1.18
     Quando
    -1.17
     Obtén
    -1.17
     why
    -1.16
    %%
    
    -1.11
    POSITIVE LOGITS
     open
    2.70
    open
    2.03
     откры
    1.93
     відкри
    1.91
     Open
    1.75
    Open
    1.63
     abiertas
    1.62
     abierto
    1.60
    開放
    1.55
    オープン
    1.52
    Activations Density 0.083%

    No Known Activations