© 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. 31-GEMMASCOPE-2-RES-262K
    7. 221867
    Prev
    Next
    INDEX
    Explanations

    waterfront, beach, dock, boat

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

    waterfront, docks, ports, and coastal towns

    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_31_width_262k_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
     subterranean
    0.49
     chlor
    0.48
     chlorine
    0.47
     backcountry
    0.44
    bromide
    0.44
     Snowdon
    0.43
    熊
    0.43
     barren
    0.43
     Brits
    0.43
     safari
    0.43
    POSITIVE LOGITS
     waterfront
    0.81
     Waterfront
    0.77
     dock
    0.73
     docks
    0.68
    dock
    0.67
     docked
    0.66
    🚤
    0.66
    ⛴
    0.66
    boat
    0.63
    Dock
    0.63
    Activations Density 0.202%

    No Known Activations