© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6419
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to mentions of prominent landmarks, structures, or titled entities (e.g., castles, court buildings, theatres, cathedrals, museums, princess/realm titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UNI
    0.74
     thuận
    0.73
    隽
    0.70
     กรรม
    0.68
    та
    0.66
     (-)
    0.66
     १९
    0.66
     (.)
    0.65
     indépendant
    0.65
     YOUNG
    0.65
    POSITIVE LOGITS
    古代
    1.09
     palaces
    1.07
     royals
    1.04
     castles
    1.01
    🏰
    0.97
     palace
    0.95
    🏺
    0.88
     князя
    0.87
     dwarves
    0.86
     dinast
    0.85
    Activations Density 1.177%

    No Known Activations