© 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. 60412
    Prev
    Next
    INDEX
    Explanations

    quarterback and related positions

    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
    عرض
    -0.77
     Técnicas
    -0.75
     Transportation
    -0.72
    王府
    -0.72
    支出
    -0.71
    难题
    -0.71
    egis
    -0.70
     Location
    -0.69
    }{\
    -0.69
    interceptor
    -0.69
    POSITIVE LOGITS
     quarterback
    1.09
     backup
    1.06
     QB
    1.03
    QB
    1.00
    Backup
    0.94
     scramble
    0.93
     quarterbacks
    0.92
     backups
    0.89
     heave
    0.88
     Backup
    0.88
    Activations Density 0.028%

    No Known Activations