© 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. 37795
    Prev
    Next
    INDEX
    Explanations

    superlatives and comparisons

    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
     lebih
    -1.30
    ütte
    -1.05
    amante
    -0.98
    ulman
    -0.96
    тко
    -0.93
    бирать
    -0.93
    hadoop
    -0.92
     fecha
    -0.91
    更多
    -0.91
     другими
    -0.91
    POSITIVE LOGITS
     most
    5.72
     best
    3.44
    最
    3.31
     greatest
    3.30
    最も
    3.06
     सबसे
    3.05
     가장
    3.00
     highest
    3.00
     largest
    2.97
    most
    2.94
    Activations Density 0.320%

    No Known Activations