© 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. 69981
    Prev
    Next
    INDEX
    Explanations

    around

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

    The neuron activates strongly on present‐participle verb forms ending in “-ing” (especially those paired with “around”).

    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
    Within
    -1.13
    Away
    -1.01
    Between
    -0.99
    between
    -0.96
     Within
    -0.93
    Up
    -0.93
     Away
    -0.91
    Péri
    -0.89
    Through
    -0.88
    Along
    -0.85
    POSITIVE LOGITS
     around
    2.47
     about
    1.89
     okolo
    1.50
     حول
    1.38
     kolem
    1.27
     около
    1.21
     körül
    1.16
     około
    1.15
     omkring
    1.09
     alambre
    1.09
    Activations Density 0.023%

    No Known Activations