© 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. 34357
    Prev
    Next
    INDEX
    Explanations

    international brands and prices

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

    This neuron detects mentions of geographic or national designators—country names, regional adjectives, and terms signaling international origin.

    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
     at
    -1.32
     four
    -1.24
     on
    -1.24
     three
    -1.19
     five
    -1.13
     intptr
    -1.10
     two
    -1.06
     all
    -1.05
     ill
    -1.02
     his
    -1.01
    POSITIVE LOGITS
    🕗
    1.23
    gypte
    1.15
    nemia
    1.15
     bera
    1.13
     melalui
    1.13
    Exciting
    1.12
     maail
    1.11
    ὕ
    1.11
     imponer
    1.11
    袿
    1.10
    Activations Density 0.005%

    No Known Activations