© 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. 79812
    Prev
    Next
    INDEX
    Explanations

    Q&A context

    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
     their
    -1.11
     birra
    -1.00
    靭
    -0.94
    FlatButton
    -0.94
    一品
    -0.93
    と
    -0.92
     vinil
    -0.91
     serai
    -0.89
     bicicleta
    -0.87
     portefeuille
    -0.87
    POSITIVE LOGITS
    ȳ
    1.05
     installé
    1.02
    urrent
    1.01
     sentía
    1.01
    
    1.00
     программа
    1.00
     emlé
    0.99
     azonban
    0.96
     própria
    0.95
    
    0.93
    Activations Density 0.002%

    No Known Activations