© 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. 91301
    Prev
    Next
    INDEX
    Explanations

    duration of 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_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
    gemeinschaft
    -1.11
     たら
    -1.04
    ſa
    -0.94
     Schauspielerin
    -0.94
     ページ
    -0.94
    värr
    -0.91
     никогда
    -0.91
     réserver
    -0.90
     め
    -0.89
    ENARIO
    -0.89
    POSITIVE LOGITS
     longer
    1.68
     for
    1.36
    longer
    1.33
     Longer
    1.20
     beyond
    1.15
     tovább
    1.08
     from
    1.08
     longest
    1.02
     awhile
    1.01
     Seconds
    1.00
    Activations Density 0.018%

    No Known Activations