© 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. 30143
    Prev
    Next
    INDEX
    Explanations

    date range expressions using BETWEEN

    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
    Negative Logits
     skup
    -0.81
     THOUGHTS
    -0.79
     COMMERCE
    -0.78
     mb
    -0.77
     key
    -0.73
    bool
    -0.71
    runtime
    -0.70
     ال
    -0.68
     REGULATIONS
    -0.68
     nh
    -0.68
    POSITIVE LOGITS
     DATE
    1.48
    DATE
    1.38
     BETWEEN
    1.27
     between
    1.13
    Between
    1.08
     date
    1.05
     Between
    1.03
     CAST
    1.02
    BETWEEN
    1.00
     TIM
    0.94
    Activations Density 0.079%

    No Known Activations