© 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. 70503
    Prev
    Next
    INDEX
    Explanations

    repetition of again

    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
     already
    -1.30
    Already
    -1.26
    already
    -1.23
     plafon
    -1.16
     כבר
    -1.11
     krep
    -1.09
    龌
    -1.09
     이미
    -1.08
     miras
    -1.06
    癭
    -1.05
    POSITIVE LOGITS
     again
    1.34
     being
    1.24
     wieder
    1.23
     снова
    1.21
     igjen
    1.20
     using
    1.12
     appear
    1.02
     Again
    1.01
    一遍
    0.98
     got
    0.98
    Activations Density 0.013%

    No Known Activations