© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 333
    Prev
    Next
    INDEX
    Explanations

    wetland and marsh habitats

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

    geographical features related to wetlands, marshes, lakes, and water bodies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mountain
    -1.19
     mountain
    -1.13
     mountainous
    -1.02
     Cave
    -1.02
     cave
    -0.98
    Mountain
    -0.98
     hilly
    -0.98
     Caves
    -0.96
     hillside
    -0.96
     MOUNTAIN
    -0.95
    POSITIVE LOGITS
     wetland
    2.02
     marsh
    1.89
     wetlands
    1.88
    marsh
    1.59
     marshes
    1.52
     Wetlands
    1.48
     Wetland
    1.44
     Marsh
    1.40
     reed
    1.40
     swamp
    1.39
    Activations Density 0.059%

    No Known Activations