© 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. 34-GEMMASCOPE-RES-131K
    7. 50038
    Prev
    Next
    INDEX
    Explanations

    sequencing words like then or after

    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_34/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
     renom
    -1.13
     mely
    -1.12
     nhiều
    -1.12
     even
    -1.10
     aunque
    -1.09
    aunque
    -1.09
     türk
    -1.09
     Wię
    -1.09
     famí
    -1.09
     Terima
    -1.08
    POSITIVE LOGITS
     then
    3.81
     afterwards
    2.38
     after
    2.27
     thereafter
    2.25
     Then
    2.22
    Then
    2.08
    然后
    2.03
     vervolgens
    1.97
    之后
    1.96
    その後
    1.96
    Activations Density 0.066%

    No Known Activations