© 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. 36117
    Prev
    Next
    INDEX
    Explanations

    user authentication fields

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

    This neuron fires on Capybara-style form-filling calls (e.g. fill_in “…user_email,” “…user_password,” etc.) in Rails feature/integration tests.

    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
    ilerin
    -0.93
    ècle
    -0.91
    etna
    -0.85
    phu
    -0.85
    |[]
    -0.82
    FXMLLoader
    -0.81
    '}';
    -0.81
     公司
    -0.81
    </>
    -0.81
    ști
    -0.80
    POSITIVE LOGITS
     desiderio
    1.01
     kepad
    0.94
     Terbaru
    0.93
    Procedimento
    0.92
     profondo
    0.91
     effectually
    0.91
    がいい
    0.90
     tranquillo
    0.89
     vuelven
    0.87
     Kondisi
    0.87
    Activations Density 0.010%

    No Known Activations