© 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. 73434
    Prev
    Next
    INDEX
    Explanations

    running, runners, race

    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
     swam
    -0.76
     croche
    -0.75
    背包
    -0.73
    keti
    -0.73
     crochet
    -0.69
     rodeo
    -0.69
     Interpolation
    -0.69
     swim
    -0.69
     nicotine
    -0.68
     swims
    -0.66
    POSITIVE LOGITS
     runners
    1.45
     Runners
    1.28
     runner
    1.27
     elite
    1.21
     Runner
    1.19
    Runners
    1.15
     running
    1.14
    Runner
    1.12
     Running
    1.08
    Running
    1.06
    Activations Density 0.020%

    No Known Activations