© 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. 106301
    Prev
    Next
    INDEX
    Explanations

    dates and discontinued periods

    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
     reopening
    -1.32
     reopen
    -1.23
     reopened
    -1.16
    Resume
    -1.09
    opening
    -1.04
    Opening
    -1.00
    resume
    -0.95
     Resume
    -0.94
    Restart
    -0.91
     revanche
    -0.89
    POSITIVE LOGITS
     cessation
    1.77
     ceased
    1.70
     ceasing
    1.68
     прекра
    1.59
     termination
    1.57
     discontin
    1.50
     ceases
    1.45
     cease
    1.40
     shut
    1.39
     shutdown
    1.38
    Activations Density 0.076%

    No Known Activations