© 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. 34-GEMMASCOPE-RES-131K
    7. 49996
    Prev
    Next
    INDEX
    Explanations

    Abu Dhabi

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

    The neuron selectively fires on named‐entity tokens—especially capitalized proper nouns and acronyms (e.g. organization and place names).

    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
    niejsze
    -0.70
    Hochspringen
    -0.67
    pard
    -0.66
    שר
    -0.63
     señales
    -0.62
    タマ
    -0.62
     всем
    -0.62
    モチ
    -0.61
    全局
    -0.61
    izos
    -0.60
    POSITIVE LOGITS
     Abu
    1.33
    Abu
    1.20
     UAE
    1.10
     Dhabi
    1.03
     ابو
    0.99
    UAE
    0.96
     Etihad
    0.88
     surrogate
    0.88
     Seychelles
    0.87
     ADN
    0.85
    Activations Density 0.016%

    No Known Activations