© 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. 93909
    Prev
    Next
    INDEX
    Explanations

    Bitcoin transaction size and limits

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on programming‐style tokens—things like header filenames and include syntax (e.g. “<…>”, “config.h”), URLs (“www”, “opensource”), identifiers (“bitcoin”, “exec”), and numeric constants—which together mark source‐code or configuration snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     статье
    -0.80
     for
    -0.75
    abung
    -0.74
     ||
    
    -0.72
     European
    -0.71
    mache
    -0.71
    borsa
    -0.70
    انگ
    -0.69
    吃的
    -0.68
     Scott
    -0.68
    POSITIVE LOGITS
     Bitcoin
    1.02
    蓠
    1.01
     wallet
    0.96
    Bitcoin
    0.96
     cryptocurrency
    0.93
     Wallet
    0.91
    }$.
    0.91
    奁
    0.91
     Sato
    0.89
     Chihuahua
    0.89
    Activations Density 0.003%

    No Known Activations