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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11925
    Prev
    Next
    INDEX
    Explanations

    desert southwest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Forest
    0.63
    森林
    0.62
     forest
    0.58
     Forest
    0.57
     FOREST
    0.56
    숲
    0.54
    forest
    0.51
    Maple
    0.50
     forests
    0.48
    青森
    0.48
    POSITIVE LOGITS
     desert
    2.41
    Desert
    2.14
     Desert
    2.13
    沙漠
    2.09
    desert
    2.08
    🏜
    1.77
     deserts
    1.77
     মরু
    1.71
    🌵
    1.61
     cacti
    1.48
    Activations Density 0.035%

    No Known Activations