© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25604
    Prev
    Next
    INDEX
    Explanations

    water and water-related entities

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

    names of water bodies and water-related entities.

    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
     spurred
    -0.82
     bolster
    -0.78
     protracted
    -0.77
     reinforces
    -0.77
     reinforce
    -0.77
     excessive
    -0.75
     alleviate
    -0.75
     embracing
    -0.74
     choosing
    -0.73
     pushes
    -0.73
    POSITIVE LOGITS
    Water
    0.90
    BUN
    0.88
    velu
    0.87
    竈
    0.82
     WATER
    0.82
     проекты
    0.81
     fli
    0.80
     水
    0.79
    gif
    0.79
     Water
    0.79
    Activations Density 0.036%

    No Known Activations