© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9160
    Prev
    Next
    INDEX
    Explanations

    locational lake names

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

    lake or loch

    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_40_width_16k_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
    邙
    0.45
    Saudi
    0.43
     оке
    0.42
    卸
    0.42
    Ocean
    0.41
    OCE
    0.39
     составляют
    0.39
     OCEAN
    0.38
    ابر
    0.38
    atlantic
    0.38
    POSITIVE LOGITS
     lake
    2.16
     lakeside
    2.14
    湖
    2.02
     Lake
    1.88
     LAKE
    1.87
    Lake
    1.80
     झील
    1.77
     lakes
    1.73
     озеро
    1.70
    lake
    1.66
    Activations Density 0.452%

    No Known Activations