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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5413
    Prev
    Next
    INDEX
    Explanations

    distance north

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

    north direction and N

    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
    滟
    0.51
     elastic
    0.50
    elastic
    0.47
     Elastic
    0.47
    Elastic
    0.45
     වි
    0.44
     plasma
    0.42
    Plasma
    0.41
    埄
    0.39
    lenie
    0.39
    POSITIVE LOGITS
     north
    4.31
     northern
    4.06
    north
    3.98
     север
    3.98
    北
    3.95
     NORTH
    3.94
    northern
    3.92
     Northern
    3.88
    NORTH
    3.86
    Northern
    3.81
    Activations Density 0.379%

    No Known Activations