© 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. 118051
    Prev
    Next
    INDEX
    Explanations

    coral reef

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

    references to coral reefs and marine ecosystems.

    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
    -0.88
    weeney
    -0.85
     Yoongi
    -0.81
     Handler
    -0.76
    ifolium
    -0.75
    Место
    -0.74
    artner
    -0.74
    delà
    -0.74
     Taehyung
    -0.73
     巧克力
    -0.73
    POSITIVE LOGITS
    builders
    0.82
     Builders
    0.81
    Builders
    0.80
    building
    0.77
    builder
    0.75
     builders
    0.75
    系统的
    0.74
    imple
    0.73
     system
    0.73
    Affirmed
    0.72
    Activations Density 0.021%

    No Known Activations