© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39386
    Prev
    Next
    INDEX
    Explanations

    events before or after time

    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
    ほとん
    -1.52
     delightfully
    -1.51
     shrewd
    -1.51
    すっ
    -1.49
    うわ
    -1.48
     unbelievably
    -1.46
     decidedly
    -1.45
     wondrous
    -1.43
    凄く
    -1.43
     exceedingly
    -1.41
    POSITIVE LOGITS
     because
    1.97
     when
    1.86
     during
    1.73
     after
    1.63
     through
    1.62
     before
    1.56
     until
    1.52
     despite
    1.50
     having
    1.49
     by
    1.48
    Activations Density 0.127%

    No Known Activations