© 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. 75604
    Prev
    Next
    INDEX
    Explanations

    headband, watt, Fc, waistband

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

    This neuron fires on capitalized tokens—e.g. product names, surnames, or other words that begin with an uppercase letter.

    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
    结语
    -2.72
    欒
    -2.34
    銚
    -2.30
    店で
    -2.23
     grasa
    -2.22
    这几
    -2.17
     hvilket
    -2.16
     amargo
    -2.14
     allmäh
    -2.09
    хіво
    -2.08
    POSITIVE LOGITS
    .
    3.61
    0
    3.05
    ↵↵
    2.72
     But
    2.61
      
    2.47
    I
    2.36
     COULD
    2.34
    我們
    2.33
    ta
    2.23
    -
    2.23
    Activations Density 0.005%

    No Known Activations