© 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. 69092
    Prev
    Next
    INDEX
    Explanations

    words starting with Sw

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

    The neuron activates on the “Sw” character sequence at the start of tokens (i.e. words beginning with “Sw,” like Swifty or Swaziland).

    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
    .
    -3.31
    al
    -2.80
    也将
    -2.61
    ()
    -2.47
    
    -2.45
    ar
    -2.36
     \
    -2.36
     of
    -2.34
     a
    -2.33
    生の
    -2.33
    POSITIVE LOGITS
    *
    2.48
     They
    2.39
    Ꮒ
    2.34
    開始
    2.33
    欉
    2.30
     However
    2.27
    釙
    2.19
     topographic
    2.14
    きました
    2.09
     Beſ
    2.08
    Activations Density 0.004%

    No Known Activations