© 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. 93109
    Prev
    Next
    INDEX
    Explanations

    before an event

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

    The neuron strongly activates on verb‐particle elements (e.g. “up,” “off,” “out,” “on”) that form phrasal‐verb constructions (e.g. “wraps up,” “rounded off,” “fly out,” “move on”).

    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
     сразу
    -1.02
    Reino
    -0.97
     empezó
    -0.97
     and
    -0.96
    先は
    -0.94
    Odpo
    -0.93
     perilaku
    -0.91
     chiller
    -0.91
     patter
    -0.91
    GEBUR
    -0.91
    POSITIVE LOGITS
     leaving
    1.39
     leave
    1.23
     departing
    1.17
     closing
    1.15
     depart
    1.07
    :
    1.07
     Leaving
    1.04
     cuối
    1.04
     send
    1.00
     Leave
    0.98
    Activations Density 0.014%

    No Known Activations