© 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. 80710
    Prev
    Next
    INDEX
    Explanations

    person won or competed

    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
     jonge
    -0.90
    }*/
    -0.90
     their
    -0.87
     krijgt
    -0.84
     deportes
    -0.82
     bağlantılar
    -0.81
    chauen
    -0.78
    кот
    -0.77
    worked
    -0.77
     new
    -0.76
    POSITIVE LOGITS
     won
    1.86
     winning
    1.81
     victories
    1.74
     wins
    1.64
     win
    1.62
     competing
    1.54
     compete
    1.54
     competes
    1.44
     competed
    1.44
    Competing
    1.42
    Activations Density 0.092%

    No Known Activations