© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17551
    Prev
    Next
    INDEX
    Explanations

    famous geographic locations

    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_31_width_65k_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
     puntos
    0.40
    
    0.39
     noting
    0.38
     topl
    0.37
    టే
    0.37
    гло
    0.35
     ვა
    0.35
     mergers
    0.35
     رست
    0.35
     points
    0.35
    POSITIVE LOGITS
     Canyon
    0.48
     Hike
    0.46
    automne
    0.46
    Waterfall
    0.46
     Hiking
    0.46
    湫
    0.45
     geologic
    0.45
     Geological
    0.45
    Hiking
    0.45
     Gorge
    0.45
    Activations Density 0.087%

    No Known Activations