© 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. 22-GEMMASCOPE-RES-131K
    4. 69000
    Prev
    Next
    INDEX
    Explanations

    XML elements and JSON keys

    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
     governador
    -1.02
     fot
    -1.02
     diferentes
    -1.01
    Präsident
    -1.00
     desiderio
    -0.99
    PARATION
    -0.98
    ाहरण
    -0.97
    遊んで
    -0.96
    幾天
    -0.95
     massimo
    -0.94
    POSITIVE LOGITS
    ,
    1.30
    .
    1.29
    millimeters
    1.04
    "
    1.03
    čo
    0.99
    '
    0.99
    sobí
    0.96
    📒
    0.96
    ón
    0.95
     иначе
    0.94
    Activations Density 0.008%

    No Known Activations