© 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. 38357
    Prev
    Next
    INDEX
    Explanations

    yards, rushing, touchdowns

    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
     getragen
    -0.79
    quim
    -0.79
     carrying
    -0.78
     carry
    -0.76
     炭
    -0.75
    做好
    -0.75
     pantallas
    -0.75
    beo
    -0.74
     angep
    -0.74
    osy
    -0.73
    POSITIVE LOGITS
     rushed
    1.26
     hundreds
    1.10
     thousands
    1.10
     thousand
    0.99
     rushing
    0.96
    Hundreds
    0.95
    Thousands
    0.95
     Thousands
    0.90
     yard
    0.88
     yards
    0.88
    Activations Density 0.010%

    No Known Activations