© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14522
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ～！
    -1.85
     gånger
    -1.85
     veck
    -1.76
    
    -1.74
    ～。
    -1.70
    ୈ
    -1.69
     gången
    -1.64
     lørdag
    -1.64
     största
    -1.59
     barna
    -1.57
    POSITIVE LOGITS
     and
    2.20
    すっ
    1.87
     decidedly
    1.81
    為に
    1.81
    おそ
    1.77
    ,;
    1.72
     brimming
    1.69
     entdeckt
    1.69
    向けの
    1.68
    きち
    1.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.