© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62394
    Prev
    Next
    INDEX
    Explanations

    dragon-type or dragon related

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

    This neuron fires most strongly on rare proper names and mythical creature terms—especially “dragon” and similar fantasy-character names.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     breathing
    -1.76
     breathe
    -1.63
     breathes
    -1.55
     fire
    -1.53
    breathing
    -1.50
     Breathing
    -1.38
     breathed
    -1.33
    呼吸
    -1.26
     breath
    -1.25
    Breathing
    -1.23
    POSITIVE LOGITS
    Dragon
    1.14
     Dragon
    1.07
     dragon
    1.06
    dragon
    1.05
    龙
    1.03
     dragons
    0.99
     Dragons
    0.98
    龍
    0.90
     DRAGON
    0.84
     Kobayashi
    0.82
    Activations Density 0.014%

    No Known Activations