© 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. 34-GEMMASCOPE-RES-131K
    4. 81496
    Prev
    Next
    INDEX
    Explanations

    United States circuit courts

    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_34/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
     通販
    -0.79
    Gbps
    -0.78
    debit
    -0.75
     Aarhus
    -0.74
    testnet
    -0.74
    Дети
    -0.73
     Gohan
    -0.72
     debit
    -0.72
     golfing
    -0.71
     fing
    -0.71
    POSITIVE LOGITS
     cards
    0.99
     card
    0.95
    cards
    0.77
     getIntent
    0.75
     Cards
    0.74
     akce
    0.74
    өздер
    0.73
     Card
    0.73
    act
    0.71
     карту
    0.69
    Activations Density 0.007%

    No Known Activations