© 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. 11118
    Prev
    Next
    INDEX
    Explanations

    such as

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

    The neuron strongly activates on the word “such,” especially when it appears in “such as” constructions introducing examples.

    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
     abiye
    -1.84
     otel
    -1.78
     rajut
    -1.73
    ครื่อง
    -1.70
    آب
    -1.69
    Але
    -1.67
    儛
    -1.64
     hırka
    -1.61
     both
    -1.58
     ney
    -1.55
    POSITIVE LOGITS
     I
    2.48
     we
    2.25
     they
    2.00
    ?
    1.91
      
    1.91
     .
    1.79
     that
    1.74
     \
    1.64
     you
    1.54
     mencion
    1.54
    Activations Density 0.048%

    No Known Activations