© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110922
    Prev
    Next
    INDEX
    Explanations

    outrage and indignation

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

    The main thing this neuron does is find instances of strong negative emotional reactions—words expressing outrage, shock, or indignation.

    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
     Each
    -1.90
    ranton
    -1.88
     It
    -1.80
    cadilly
    -1.78
     barva
    -1.74
     будет
    -1.72
     Большая
    -1.67
    "))
    -1.64
     There
    -1.63
     karena
    -1.63
    POSITIVE LOGITS
     vraiment
    1.94
     nimmer
    1.80
     simpel
    1.76
     nowe
    1.73
     olie
    1.70
     maler
    1.70
     hals
    1.68
     potensi
    1.62
     spektak
    1.62
     LEE
    1.59
    Activations Density 0.014%

    No Known Activations