© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104264
    Prev
    Next
    INDEX
    Explanations

    naming things

    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
     ponownie
    -0.96
     mechanism
    -0.92
     conversing
    -0.85
     provide
    -0.84
     împ
    -0.84
     arrange
    -0.82
    可以看到
    -0.81
    いっぱ
    -0.80
    ervi
    -0.80
     Stoll
    -0.79
    POSITIVE LOGITS
    互联网档案馆
    1.13
    dienne
    1.07
    rename
    0.99
    名称
    0.97
     naming
    0.96
    
    0.96
    kening
    0.96
     LCCN
    0.95
     capítulos
    0.94
    Conclusie
    0.93
    Activations Density 0.147%

    No Known Activations