© 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. 67764
    Prev
    Next
    INDEX
    Explanations

    continuous learning and knowledge acquisition

    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
     illustratie
    -1.13
    ございません
    -1.12
    essayer
    -1.12
    ないです
    -1.09
    explique
    -1.07
    鎳
    -1.07
     allé
    -1.05
    arono
    -1.02
    artiges
    -1.02
     beoor
    -1.02
    POSITIVE LOGITS
     learning
    1.70
     improve
    1.32
     research
    1.31
     constantly
    1.28
     continuously
    1.27
     continually
    1.26
     knowledge
    1.22
     постоянно
    1.22
     new
    1.22
     upgrading
    1.21
    Activations Density 0.028%

    No Known Activations