© 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. 93830
    Prev
    Next
    INDEX
    Explanations

    contracts, messages, addresses

    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
    swire
    -0.87
    ἶ
    -0.81
     MONEY
    -0.79
     fã
    -0.78
     sull
    -0.77
     پذیر
    -0.77
     iria
    -0.76
    quela
    -0.76
     ACCEPT
    -0.75
    balleur
    -0.75
    POSITIVE LOGITS
     msg
    1.71
    msg
    1.48
     owner
    1.16
     MSG
    1.10
    msgSender
    1.09
     address
    1.09
     message
    1.08
     Msg
    1.07
    MSG
    0.97
     addresses
    0.95
    Activations Density 0.003%

    No Known Activations