© 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. 34-GEMMASCOPE-RES-131K
    7. 102605
    Prev
    Next
    INDEX
    Explanations

    Ethereum Web3 programming

    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
     пласти
    -0.73
     controlar
    -0.71
    limard
    -0.71
    chand
    -0.70
    bbons
    -0.70
    Rod
    -0.69
    versite
    -0.69
    tigma
    -0.68
     orilla
    -0.68
     belum
    -0.68
    POSITIVE LOGITS
     Ether
    1.43
     ether
    1.42
     ethers
    1.34
     eth
    1.34
     wei
    1.29
    Ether
    1.27
    ether
    1.23
     gas
    1.20
     ABI
    1.19
     Eth
    1.12
    Activations Density 0.040%

    No Known Activations