© 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. 22-GEMMASCOPE-RES-131K
    7. 73718
    Prev
    Next
    INDEX
    Explanations

    viewDidLoad method

    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
     eki
    -1.15
     kask
    -1.09
     bakteri
    -1.00
     eksper
    -1.00
     ekst
    -1.00
     spesifik
    -0.98
     nabo
    -0.98
     praktis
    -0.98
     galeri
    -0.97
    wohner
    -0.96
    POSITIVE LOGITS
     cherchez
    1.05
     informatie
    0.99
     souhaitez
    0.91
     aliviar
    0.90
     hábit
    0.90
     aurez
    0.90
    ühen
    0.90
     cantantes
    0.89
     điệu
    0.89
     instead
    0.89
    Activations Density 0.002%

    No Known Activations