© 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. 401
    Prev
    Next
    INDEX
    Explanations

    Bitcoin mining

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

    The neuron fires most strongly on technical or quantitative language—numbers, units, and domain-specific specs (e.g. mining rates, years, data-center power, “nuclear-capable,” API calls, etc.).

    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
     aéreo
    -0.80
    ressa
    -0.75
     lẻ
    -0.75
    イエ
    -0.74
     Launches
    -0.71
     Replies
    -0.70
     spawns
    -0.69
    dinosaur
    -0.68
     peny
    -0.68
    danh
    -0.68
    POSITIVE LOGITS
     mining
    1.15
     Bitcoin
    1.04
     miners
    1.01
     miner
    0.98
     bitcoin
    0.93
     BTC
    0.92
    mining
    0.91
     machines
    0.87
     hosting
    0.86
     Mining
    0.86
    Activations Density 0.021%

    No Known Activations