© 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. 92259
    Prev
    Next
    INDEX
    Explanations

    join our community

    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
    entire
    -1.10
     ganzen
    -1.08
     gesamten
    -1.05
     gesamte
    -1.02
     entire
    -0.94
     ENTIRE
    -0.93
     komplet
    -0.89
     ganze
    -0.84
     Entire
    -0.84
    whole
    -0.83
    POSITIVE LOGITS
     ranks
    1.91
    行列
    1.87
     fold
    1.74
     family
    1.65
     team
    1.65
     roster
    1.50
     bandwagon
    1.46
     tribe
    1.45
     fray
    1.41
     queue
    1.37
    Activations Density 0.065%

    No Known Activations