© 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. 336
    Prev
    Next
    INDEX
    Explanations

    habitats, ecosystems, water

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

    words and phrases related to natural environments, wildlife, and ecological systems.

    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
     feedbacks
    -0.92
    栽培
    -0.92
     sensu
    -0.91
     puissant
    -0.89
    ίων
    -0.87
     siège
    -0.86
     दिल्ली
    -0.85
     gato
    -0.82
     greasy
    -0.81
     mori
    -0.79
    POSITIVE LOGITS
     mating
    0.99
     ekos
    0.94
     extinción
    0.93
     runoff
    0.92
     pemandangan
    0.91
    urdy
    0.89
     ecosystems
    0.88
     indigenous
    0.88
     ecosystem
    0.88
     replen
    0.88
    Activations Density 0.106%

    No Known Activations