© 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. 65788
    Prev
    Next
    INDEX
    Explanations

    banknotes polymer security features

    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
     coins
    -1.28
     coin
    -1.21
     Coin
    -0.97
     coined
    -0.94
     médaille
    -0.93
     coinage
    -0.90
     моне
    -0.89
     Coins
    -0.84
    coins
    -0.83
    コイン
    -0.81
    POSITIVE LOGITS
     polymer
    1.05
    polymer
    0.92
     Polymer
    0.83
     watermark
    0.81
     security
    0.79
    eficent
    0.78
     replacing
    0.77
     serial
    0.77
    agriculture
    0.75
    vances
    0.74
    Activations Density 0.007%

    No Known Activations