© 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. 34-GEMMASCOPE-RES-131K
    7. 117843
    Prev
    Next
    INDEX
    Explanations

    locations for events

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

    The neuron fires on temporal and locational markers (e.g. “on,” “at”) that introduce dates, times, or event venues.

    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
     balcón
    -0.78
    sproz
    -0.76
    OOO
    -0.74
    friday
    -0.73
    fD
    -0.73
    スタッフ
    -0.72
     estante
    -0.72
    monday
    -0.71
     drog
    -0.71
    接口
    -0.71
    POSITIVE LOGITS
     auditorium
    1.73
     ballroom
    1.58
     venue
    1.43
     hall
    1.42
     venues
    1.35
     headquarters
    1.23
     convention
    1.16
     clubhouse
    1.15
     Auditorium
    1.15
     conference
    1.13
    Activations Density 0.076%

    No Known Activations