© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25627
    Prev
    Next
    INDEX
    Explanations

    geographical locations

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

    The neuron activates on geographic place names (cities, regions, countries).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    の方法
    -1.27
    になったら
    -1.20
     in
    -1.20
     semplici
    -1.19
     raccol
    -1.16
     straordin
    -1.13
     davvero
    -1.10
    の紹介
    -1.05
     giusti
    -1.02
    久し
    -1.02
    POSITIVE LOGITS
    alue
    1.11
     where
    1.11
     الشاشة
    1.10
     nachdem
    1.08
     womit
    1.07
    でしょうね
    1.06
     deras
    1.05
     tages
    1.04
     distante
    1.04
     sacerdote
    1.03
    Activations Density 0.100%

    No Known Activations