© 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. 68931
    Prev
    Next
    INDEX
    Explanations

    updates and changes

    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
    gyű
    -0.91
    ambiguation
    -0.88
     pomys
    -0.87
    äť
    -0.85
    られました
    -0.84
     разгово
    -0.81
     reducción
    -0.80
    koľ
    -0.79
     первым
    -0.78
     різних
    -0.78
    POSITIVE LOGITS
     changes
    2.20
     updates
    1.84
    更新
    1.83
     update
    1.80
     change
    1.79
     обнов
    1.62
     updating
    1.57
     updated
    1.52
     changed
    1.49
     changing
    1.48
    Activations Density 0.169%

    No Known Activations