© 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. 103777
    Prev
    Next
    INDEX
    Explanations

    for a duration

    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
     until
    -1.25
     remaining
    -1.16
     jusqu
    -1.14
     first
    -1.13
     later
    -1.12
     after
    -1.11
     afterwards
    -1.00
     in
    -0.98
     having
    -0.98
     up
    -0.96
    POSITIVE LOGITS
     since
    1.99
    since
    1.46
     منذ
    1.44
    Less
    1.43
    almost
    1.37
    Since
    1.32
     depuis
    1.29
    nearly
    1.29
     snart
    1.27
     longer
    1.26
    Activations Density 0.041%

    No Known Activations