© 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. 130673
    Prev
    Next
    INDEX
    Explanations

    scrolling down

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

    The neuron activates on instructions or mentions of “scroll down” (i.e., user scrolling or being prompted to scroll down the page).

    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
     ALWAYS
    -1.96
     EVERY
    -1.61
     TWO
    -1.55
     NEVER
    -1.48
     with
    -1.46
     Those
    -1.46
     Aside
    -1.44
     ONLY
    -1.42
     both
    -1.41
     ONE
    -1.38
    POSITIVE LOGITS
    ’
    1.84
     to
    1.75
    炱
    1.68
    鰨
    1.56
    
    1.52
    e
    1.47
    </strong>
    1.45
     ſol
    1.45
     belangrijk
    1.44
     brillant
    1.43
    Activations Density 0.017%

    No Known Activations