© 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. 22-GEMMASCOPE-RES-131K
    7. 130876
    Prev
    Next
    INDEX
    Explanations

    scientific or technical jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     لیتر
    -0.97
     without
    -0.94
     bataille
    -0.91
     unrelenting
    -0.90
     cliquant
    -0.90
     groundbreaking
    -0.89
     demonstrates
    -0.88
     Moder
    -0.88
     丘
    -0.88
     ingrained
    -0.88
    POSITIVE LOGITS
     myriad
    1.10
    HideInInspector
    0.99
     revamped
    0.98
     لأنه
    0.94
    overview
    0.94
    column
    0.93
     réduire
    0.92
    address
    0.92
     continually
    0.91
    caches
    0.91
    Activations Density 0.012%

    No Known Activations