© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64369
    Prev
    Next
    INDEX
    Explanations

    time passing, recurrence, 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
    Negative Logits
     ventanas
    -1.05
     quedado
    -0.98
     étend
    -0.96
     célè
    -0.94
     écout
    -0.94
     judíos
    -0.93
     tenido
    -0.93
    satis
    -0.92
     comenzado
    -0.91
     dépens
    -0.91
    POSITIVE LOGITS
     again
    1.54
     same
    1.47
     erneut
    1.15
    再び
    1.14
     nochmal
    1.14
    再度
    1.13
     repeat
    1.12
     remembered
    1.09
     다시
    1.05
     nuovamente
    1.05
    Activations Density 0.069%

    No Known Activations