© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    impulse action, power, or type

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

    The neuron consistently activates on occurrences of the word “impulse.”

    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
    真的是
    -2.73
    of
    -2.69
     tématu
    -2.61
     支援
    -2.58
    jenigen
    -2.58
    事實
    -2.55
     momentous
    -2.50
    
    -2.47
     sumptuous
    -2.47
     monumental
    -2.47
    POSITIVE LOGITS
    也将
    2.41
     egip
    2.34
     barcel
    2.30
     digitais
    2.25
     homen
    2.25
     jos
    2.25
     держать
    2.20
     FEBR
    2.20
    采用了
    2.20
     For
    2.19
    Activations Density 0.011%

    No Known Activations