© 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. 120015
    Prev
    Next
    INDEX
    Explanations

    PDE inhibitors, MTT assay, mindless drone

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

    scientific acronyms and technical terms, particularly PDE (partial differential equation) and related scientific terminology.

    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
     “
    -3.05
    ↵
    -3.03
    "
    -2.73
    :
    -2.61
     ”
    -2.59
    ”:
    -2.56
    </h3>
    -2.52
    c
    -2.48
    ]
    -2.45
    ↵↵
    -2.44
    POSITIVE LOGITS
    鹛
    3.09
     is
    2.92
    咘
    2.91
    虓
    2.86
    螄
    2.80
     inond
    2.78
    騭
    2.70
    
    2.67
     menant
    2.63
    鸶
    2.61
    Activations Density 0.005%

    No Known Activations