© 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. 87177
    Prev
    Next
    INDEX
    Explanations

    authenticated signed memorabilia

    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
     sparkly
    -0.88
     healthful
    -0.84
    解决方案
    -0.79
     invigor
    -0.77
     atacante
    -0.77
     sooooo
    -0.77
     prejudicial
    -0.75
     stately
    -0.75
    Ficha
    -0.73
     gill
    -0.73
    POSITIVE LOGITS
     authentication
    1.00
     COA
    1.00
    COA
    0.93
     Authentication
    0.92
     Beckett
    0.91
    signed
    0.90
     memorabilia
    0.89
    odule
    0.87
    Authenticated
    0.85
     Signed
    0.84
    Activations Density 0.012%

    No Known Activations