© 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. 22-GEMMASCOPE-RES-131K
    7. 67628
    Prev
    Next
    INDEX
    Explanations

    PR followed by specific suffixes

    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_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
     ‘
    -3.81
    </strong>
    -3.63
     `
    -2.88
     ?
    -2.80
    "
    -2.78
     ‚
    -2.67
    ↵
    -2.66
    <strong>
    -2.61
    is
    -2.56
      
    -2.53
    POSITIVE LOGITS
    瑧
    3.03
    鬭
    2.61
     花纹
    2.61
     Sejarah
    2.58
     短发
    2.56
    
    2.53
     esquer
    2.52
     rajut
    2.48
     zustand
    2.45
    ㍉
    2.44
    Activations Density 0.040%

    No Known Activations