© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71091
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript imports

    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
     Proz
    -1.09
     inadequate
    -1.08
     AspNetCore
    -1.07
    resave
    -1.05
    Uart
    -1.03
     Hombre
    -1.02
     ensuring
    -0.96
     gentil
    -0.95
    ШЕ
    -0.93
    澱
    -0.93
    POSITIVE LOGITS
     satisfacer
    1.09
     proveedores
    1.06
     investimentos
    1.02
     práci
    1.01
     fatores
    0.98
     ingresos
    0.98
    tığı
    0.97
    ↵↵
    0.96
     practicar
    0.96
     vstup
    0.96
    Activations Density 0.002%

    No Known Activations