© 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. 10-GEMMASCOPE-RES-131K
    7. 104636
    Prev
    Next
    INDEX
    Explanations

    terrestrial populations and ecosystems

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

    The neuron detects the word "terrestrial" in scientific and technical contexts.

    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_10/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
    赑
    -3.30
    
    -3.20
    饪
    -3.20
    羕
    -3.11
    棡
    -3.06
    厛
    -3.03
     内衣
    -3.02
    釭
    -2.94
    ⵈ
    -2.91
    鵙
    -2.91
    POSITIVE LOGITS
    "
    3.38
    }
    3.16
     That
    3.16
     unparalleled
    3.00
    of
    2.89
    ??
    2.78
    大部分
    2.73
     notable
    2.72
     They
    2.69
    ;
    2.66
    Activations Density 0.004%

    No Known Activations