© 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. 12186
    Prev
    Next
    INDEX
    Explanations

    chronograph, perpetual calendar

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

    The neuron fires on mentions of specific watches—brand names and model references in the text.

    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
     Unterkunft
    -0.78
     interpreter
    -0.76
     wrote
    -0.75
    あった
    -0.69
     colon
    -0.69
    cdef
    -0.68
    وافق
    -0.67
    됬
    -0.67
     gold
    -0.67
     workers
    -0.66
    POSITIVE LOGITS
     Yoshida
    0.88
     dealer
    0.81
     airbags
    0.79
    ▪
    0.78
     exemplaire
    0.78
    Allemagne
    0.77
     summon
    0.77
     Dealer
    0.76
     вересня
    0.75
     WeChat
    0.75
    Activations Density 0.011%

    No Known Activations