© 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. 10-GEMMASCOPE-RES-131K
    7. 71181
    Prev
    Next
    INDEX
    Explanations

    participatory activities

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

    The neuron fires on words and phrases signaling active participation or engagement (e.g. participation, involvement, engagement).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     bemerken
    -1.35
     vertraut
    -1.27
     grossen
    -1.27
    2
    -1.24
    4
    -1.23
     forskj
    -1.23
     Verlust
    -1.23
    1
    -1.19
    Putting
    -1.18
    3
    -1.18
    POSITIVE LOGITS
     только
    1.69
     тільки
    1.66
    ໌
    1.50
     flesta
    1.49
    medriver
    1.47
     seulement
    1.43
    郢
    1.40
    рных
    1.34
    anmar
    1.33
    ureka
    1.33
    Activations Density 0.034%

    No Known Activations