© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5788
    Prev
    Next
    INDEX
    Explanations

    neighbourhood or QUAD nations

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

    India's borders and China

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    ₦
    0.48
     घोड़
    0.47
    农村
    0.47
    Cro
    0.46
     ફક્ત
    0.44
    ร่
    0.43
     জমিদার
    0.43
    涤
    0.43
    Atlas
    0.43
    Rural
    0.42
    POSITIVE LOGITS
     QUAD
    0.70
     Neighbourhood
    0.62
     neighbourhood
    0.60
     Quad
    0.57
     neighbours
    0.52
     till
    0.50
     maritime
    0.50
    ਜ਼
    0.49
    neighbour
    0.49
    QUAD
    0.49
    Activations Density 0.031%

    No Known Activations