© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55807
    Prev
    Next
    INDEX
    Explanations

    award nominations and wins

    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
     without
    -1.00
     new
    -0.94
     important
    -0.86
     even
    -0.85
     etc
    -0.85
     Emmy
    -0.84
     by
    -0.84
     one
    -0.83
     Grammy
    -0.83
     or
    -0.83
    POSITIVE LOGITS
     kategori
    1.23
    Congratulations
    1.22
     deserving
    1.13
    Outstanding
    1.09
     nominees
    1.08
     congratulations
    1.07
     kategor
    1.06
    Innovative
    1.05
    overall
    1.02
    category
    1.02
    Activations Density 0.024%

    No Known Activations