© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3380
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on mentions of airport or airline priority check-in (e.g., “check-in,” “in,” “counters,” “Business Class”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     транспорти
    0.67
     футбол
    0.67
    쏜
    0.65
     баскетбол
    0.64
     cooking
    0.60
     tov
    0.59
    🍗
    0.59
     privata
    0.58
    🚽
    0.57
    邀请
    0.57
    POSITIVE LOGITS
     cashier
    1.37
     receptionist
    1.08
     check
    1.01
     clerk
    1.01
     register
    0.99
     Check
    0.98
    Check
    0.98
    register
    0.98
    Register
    0.96
    check
    0.95
    Activations Density 0.320%

    No Known Activations