© 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. 34-GEMMASCOPE-RES-131K
    4. 118084
    Prev
    Next
    INDEX
    Explanations

    U2 Bono achtuing baby U2 Bono speling bee sandrine clet guet code

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

    The neuron fires on mentions of music titles and proper names—especially references to the band U2 (their name, albums, songs, etc.).

    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
     morale
    -0.80
    bouncy
    -0.75
     tener
    -0.71
    accoon
    -0.70
     گوید
    -0.68
     smiled
    -0.67
     parlament
    -0.67
     breve
    -0.65
     هذا
    -0.65
    phinx
    -0.65
    POSITIVE LOGITS
     Bono
    1.54
    Achtung
    1.05
     bono
    0.94
     Vertigo
    0.93
     Achtung
    0.90
     économie
    0.85
     Zoo
    0.84
     ies
    0.82
    renderItem
    0.82
    bono
    0.81
    Activations Density 0.011%

    No Known Activations