© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117613
    Prev
    Next
    INDEX
    Explanations

    event and meeting spaces

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

    The neuron strongly activates on words denoting organized events or meeting venues (e.g. meeting, conference, reception, gathering, function, event).

    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
    就知道
    -0.83
     of
    -0.78
     beschäftigt
    -0.74
     několik
    -0.72
     beschäf
    -0.72
     veröffentlich
    -0.71
     überprü
    -0.71
     Орден
    -0.70
    zen
    -0.70
     což
    -0.70
    POSITIVE LOGITS
     room
    2.30
     hall
    2.14
     rooms
    2.06
     space
    1.76
    room
    1.65
     spaces
    1.60
     facilities
    1.59
     Room
    1.56
    raum
    1.52
    室
    1.52
    Activations Density 0.022%

    No Known Activations