© 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. 9322
    Prev
    Next
    INDEX
    Explanations

    trip or stumble upon something

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

    The neuron fires on occurrences of “trip” (e.g. trip, tripping) and especially the phrase “tripping hazards.”

    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
    _
    -2.31
    m
    -2.03
    se
    -2.00
    ta
    -1.95
    {
    -1.93
    h
    -1.85
    f
    -1.80
    i
    -1.78
    o
    -1.78
    n
    -1.77
    POSITIVE LOGITS
    
    2.00
     sốt
    1.80
    anyeol
    1.78
    ⟐
    1.70
    𐬹
    1.70
     خبرگزاری
    1.70
    ዣ
    1.70
    鹛
    1.66
    
    1.64
    伷
    1.63
    Activations Density 0.006%

    No Known Activations