© 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. 23444
    Prev
    Next
    INDEX
    Explanations

    underwater activities and marine life

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

    content related to underwater activities like snorkeling, scuba diving, and marine life.

    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
     riverside
    -0.99
     Санкт
    -0.90
    ariConfig
    -0.87
     Truppen
    -0.82
     niebla
    -0.81
     зву
    -0.79
     riparian
    -0.79
    ELEV
    -0.79
    üğü
    -0.79
    chtest
    -0.78
    POSITIVE LOGITS
     coral
    1.94
     reefs
    1.73
     reef
    1.70
     snorkeling
    1.68
    coral
    1.59
     corals
    1.57
     snorkel
    1.45
     underwater
    1.41
     dive
    1.23
     Reef
    1.23
    Activations Density 0.023%

    No Known Activations