© 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. 27927
    Prev
    Next
    INDEX
    Explanations

    statistical leaders and parameters

    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
     adduced
    -0.97
    วิธี
    -0.90
    SAMPLES
    -0.86
     потрі
    -0.81
     разбира
    -0.79
    Вариант
    -0.79
     introducido
    -0.79
    授業
    -0.79
    ชน
    -0.78
    jetivo
    -0.77
    POSITIVE LOGITS
     characteristics
    1.38
     parameters
    1.30
     information
    1.30
     statistics
    1.27
     facts
    1.18
     things
    1.18
     attributes
    1.16
     stats
    1.16
     data
    1.13
     metrics
    1.10
    Activations Density 0.248%

    No Known Activations