© 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. 102458
    Prev
    Next
    INDEX
    Explanations

    sports car, best friend, awakenings

    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
     eachother
    -1.38
     velmi
    -1.27
    っており
    -1.20
     reccomend
    -1.14
     Vám
    -1.11
    沢山
    -1.05
     dámské
    -1.02
    ntä
    -1.02
    远处
    -1.02
     mohou
    -1.02
    POSITIVE LOGITS
     damn
    1.15
     hadn
    1.09
    Acknowledgments
    1.07
     wasn
    1.07
     رسانی
    1.02
    一九
    1.01
    Ｄ
    0.99
     didn
    0.98
     OMITTED
    0.98
     reafon
    0.98
    Activations Density 0.048%

    No Known Activations