© 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. 103168
    Prev
    Next
    INDEX
    Explanations

    numbers and 'that'

    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
     przyp
    -0.87
    pady
    -0.85
    شرين
    -0.83
     Diciembre
    -0.82
    予選
    -0.80
     meneg
    -0.79
    ၆
    -0.78
     syarat
    -0.77
     henvis
    -0.77
    éget
    -0.76
    POSITIVE LOGITS
    1
    1.66
    １
    1.42
     ۱
    1.14
    𝟏
    0.91
    ۱
    0.90
    ¹
    0.85
     Vara
    0.84
    
    0.84
     ১
    0.83
     ١
    0.82
    Activations Density 0.012%

    No Known Activations