© 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. 10-GEMMASCOPE-RES-131K
    4. 12059
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     vermelhas
    -1.31
    angebot
    -1.30
     engraçadas
    -1.30
    ynchronously
    -1.23
    墙壁
    -1.19
    cessed
    -1.17
     vack
    -1.16
     lekker
    -1.15
     dras
    -1.15
    trze
    -1.14
    POSITIVE LOGITS
     other
    1.14
    <b>
    1.12
    льше
    1.07
     has
    1.06
     неба
    1.05
     note
    1.02
    )
    
    
    1.01
     다른
    0.98
    maris
    0.98
    後的
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.