© 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. 73463
    Prev
    Next
    INDEX
    Explanations

    and followed by roles

    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
     både
    -2.03
     différents
    -1.66
     diverses
    -1.63
    
    -1.60
     pernic
    -1.54
     diversos
    -1.52
     Dinas
    -1.48
    鳚
    -1.45
     relevante
    -1.45
     verschillende
    -1.42
    POSITIVE LOGITS
     one
    2.38
     now
    2.27
     former
    2.06
     longtime
    1.96
     long
    1.95
     first
    1.93
     frequent
    1.89
     continual
    1.82
     newly
    1.79
     new
    1.77
    Activations Density 0.061%

    No Known Activations