© 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. 54074
    Prev
    Next
    INDEX
    Explanations

    fields and rings

    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
     Milwaukee
    -0.83
     Mayor
    -0.75
     Simpson
    -0.74
     Junction
    -0.71
    🥩
    -0.70
    kPa
    -0.70
     Grammy
    -0.69
     escuela
    -0.68
     Memphis
    -0.68
    }{%
    -0.67
    POSITIVE LOGITS
     ring
    1.56
     field
    1.52
     fields
    1.42
     rings
    1.34
    Ring
    1.30
     polynomial
    1.30
    Field
    1.25
    ring
    1.23
    field
    1.17
     Field
    1.15
    Activations Density 0.122%

    No Known Activations