© 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. 10-GEMMASCOPE-RES-131K
    7. 111441
    Prev
    Next
    INDEX
    Explanations

    dimensions of matrices and theories

    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_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
     Añade
    -2.20
    ,  
    -2.19
     estrema
    -2.09
     Wszyst
    -2.05
     helicópter
    -2.00
     sicura
    -1.98
    gucig
    -1.98
    ícios
    -1.95
     nastro
    -1.95
     現貨
    -1.91
    POSITIVE LOGITS
    \
    2.48
     –
    2.02
        
    1.95
      
    1.84
    ⤥
    1.83
            
    1.71
     ו
    1.70
    更に
    1.65
    先に
    1.61
     pero
    1.57
    Activations Density 0.015%

    No Known Activations