© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14790
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     more
    -2.55
     that
    -2.38
     some
    -2.28
     many
    -2.05
     only
    -1.98
     most
    -1.98
     probably
    -1.98
     new
    -1.94
     now
    -1.89
     less
    -1.73
    POSITIVE LOGITS
    งิน
    2.02
     sebut
    1.98
     primeiros
    1.97
    部分は
    1.96
    攥
    1.95
    饹
    1.93
     蝶
    1.92
    澌
    1.91
    
    1.91
    瞜
    1.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.