© 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. 46271
    Prev
    Next
    INDEX
    Explanations

    Fintech onboarding blockchain metaverse

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

    Fintech, blockchain, metaverse, transformative

    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
    are
    0.48
     stets
    0.45
     Workmen
    0.45
    잌
    0.45
     který
    0.44
     varit
    0.44
     numerosi
    0.44
     পাশে
    0.44
     Temperaturen
    0.43
     alleen
    0.42
    POSITIVE LOGITS
     omnichannel
    0.68
     Fintech
    0.64
     fintech
    0.61
    ⁣⁣
    0.59
     transformative
    0.56
     трансформа
    0.55
     metaverse
    0.53
     onboarding
    0.52
     Blockchain
    0.52
    Blockchain
    0.52
    Activations Density 0.000%

    No Known Activations