© 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. 68940
    Prev
    Next
    INDEX
    Explanations

    planned events and arrangements

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

    The neuron strongly activates on multiword proper names—especially venues, events, or businesses (e.g. “Adelaide Festival Theatre,” “catering business”).

    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
    すぎて
    -0.86
     dziś
    -0.84
     modernized
    -0.83
    过去的
    -0.81
     defunct
    -0.80
     każdego
    -0.80
     unsustainable
    -0.79
     kiedyś
    -0.79
     obecnie
    -0.77
    新たな
    -0.77
    POSITIVE LOGITS
     planned
    1.49
     scheduled
    1.38
    planned
    1.27
     important
    1.13
     crucial
    1.05
    楽しみにして
    1.05
     SCHE
    1.05
     plans
    1.03
    scheduled
    1.02
     delikat
    1.02
    Activations Density 0.034%

    No Known Activations