© 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. 84512
    Prev
    Next
    INDEX
    Explanations

    soon, eventually, later

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

    The neuron fires on code tokens related to CSS/jQuery animations—namely the “animated” class names (e.g. ZoomIn, Down, Shake) and the numeric parameters (durations) passed to animation methods.

    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
     limone
    -0.85
    申し上げます
    -0.84
     ivi
    -0.82
     piu
    -0.80
     Igu
    -0.80
     ihop
    -0.80
     mixt
    -0.80
     sond
    -0.79
     jord
    -0.79
     goku
    -0.78
    POSITIVE LOGITS
     soon
    1.71
     eventually
    1.65
     eventual
    1.38
     setTimeout
    1.31
     shortly
    1.30
    setTimeout
    1.26
     until
    1.20
    eventually
    1.20
     Eventually
    1.18
     later
    1.15
    Activations Density 0.004%

    No Known Activations