© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16295
    Prev
    Next
    INDEX
    Explanations

    blockchain and cryptocurrencies

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

    cryptocurrency and blockchain technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    髌
    0.73
    颞
    0.71
    镗
    0.63
     мебель
    0.61
     хими
    0.60
     Drury
    0.57
     брига
    0.57
    翮
    0.56
    年龄
    0.56
     tcpHeader
    0.56
    POSITIVE LOGITS
     blockchain
    1.88
     Ethereum
    1.77
     crypto
    1.74
     cryptocurrency
    1.73
     Bitcoin
    1.70
     Blockchain
    1.66
     cryptocur
    1.63
    Ethereum
    1.62
    Blockchain
    1.61
     DeFi
    1.56
    Activations Density 0.131%

    No Known Activations