© 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. 56719
    Prev
    Next
    INDEX
    Explanations

    years or year ranges

    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
     starts
    -1.24
     begins
    -1.20
     begin
    -1.14
     начинается
    -1.05
     start
    -1.05
     began
    -0.97
     started
    -0.96
    เริ่ม
    -0.92
     beginning
    -0.91
    føre
    -0.88
    POSITIVE LOGITS
     cessation
    1.40
     termination
    1.27
     ending
    1.26
    结束
    1.19
     ukon
    1.11
     zakoń
    1.09
     discontin
    1.08
     koniec
    1.05
    stopped
    1.05
     завер
    1.03
    Activations Density 0.089%

    No Known Activations