© 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. 47176
    Prev
    Next
    INDEX
    Explanations

    first look or hint

    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
     Toolkit
    -0.85
    cimento
    -0.84
      
    -0.80
    machung
    -0.79
    IATION
    -0.77
    ]]]
    -0.76
    awn
    -0.75
     ?</
    -0.75
     ANALYSIS
    -0.75
     Prompt
    -0.75
    POSITIVE LOGITS
     glimpse
    4.75
     glimpses
    4.34
     glimp
    2.83
    gli
    2.44
    Gli
    2.36
     Gli
    2.13
     peek
    2.05
     hints
    2.00
     view
    1.89
     gli
    1.88
    Activations Density 0.037%

    No Known Activations