© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81289
    Prev
    Next
    INDEX
    Explanations

    events and gatherings

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

    The neuron fires on mentions of scheduled events, especially when paired with dates, times, or numbered competitions.

    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
    oproject
    -0.99
    建立
    -0.91
     тогда
    -0.91
     asupra
    -0.82
     investigated
    -0.80
     istnie
    -0.80
    Coming
    -0.80
    corr
    -0.79
     groups
    -0.79
     respald
    -0.79
    POSITIVE LOGITS
     held
    0.98
     kaldır
    0.88
     diras
    0.85
     mawar
    0.84
    Kval
    0.82
     kotor
    0.81
     grandeur
    0.81
    ImageButton
    0.79
    iglio
    0.78
     witness
    0.77
    Activations Density 0.035%

    No Known Activations