© 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. 34-GEMMASCOPE-RES-131K
    7. 3450
    Prev
    Next
    INDEX
    Explanations

    after "then"

    np_acts-logits-general · gemini-2.5-flash-lite

    the passage about the new graphical, mouse-driven interface for the war game—i.e. terms describing computer GUI features.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     currently
    -2.53
     obecnie
    -2.22
    Currently
    -2.13
     actualmente
    -2.05
     today
    -2.03
     actuellement
    -1.94
     attualmente
    -1.88
     presently
    -1.87
     derzeit
    -1.85
    Actualmente
    -1.82
    POSITIVE LOGITS
     then
    3.81
     тогда
    3.27
     entonces
    2.73
     então
    2.73
     damals
    2.63
     allora
    2.45
     alors
    2.34
    then
    2.33
     Then
    2.19
     damaligen
    2.19
    Activations Density 0.135%

    No Known Activations