© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48530
    Prev
    Next
    INDEX
    Explanations

    load more

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

    The neuron fires strongly on descriptions of an “infinite scroll” user‐interface pattern—phrases about the user scrolling down the page and more results being loaded.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    sistencia
    -0.81
    ካ
    -0.81
    дакти
    -0.81
     Verona
    -0.80
    erschrank
    -0.79
    рои
    -0.77
     alternatif
    -0.77
     asla
    -0.75
    Exeunt
    -0.75
     Yankee
    -0.74
    POSITIVE LOGITS
     load
    1.78
     more
    1.72
    LoadMore
    1.60
     Load
    1.59
    loadMore
    1.52
    more
    1.49
     next
    1.40
     LOAD
    1.34
     bottom
    1.28
     loading
    1.28
    Activations Density 0.028%

    No Known Activations