© 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. 8395
    Prev
    Next
    INDEX
    Explanations

    cardinal directions

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

    east and directions

    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
    駋
    0.43
    ندگان
    0.40
    жига
    0.39
     Пів
    0.38
    द्दल
    0.38
     القب
    0.38
    ]&
    0.37
    fyd
    0.36
    вропей
    0.36
     accents
    0.36
    POSITIVE LOGITS
    east
    1.05
     east
    1.02
     northeast
    0.93
     شرق
    0.88
    東
    0.86
    东
    0.85
     southeast
    0.84
    East
    0.81
    west
    0.79
     west
    0.79
    Activations Density 0.031%

    No Known Activations