© 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. 79544
    Prev
    Next
    INDEX
    Explanations

    things to avoid

    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
    証
    -0.93
    
    -0.88
    ynchronously
    -0.81
    folgung
    -0.80
     πρω
    -0.79
    不了
    -0.77
     zout
    -0.77
     lema
    -0.75
    Explanation
    -0.75
     层
    -0.75
    POSITIVE LOGITS
     pitfalls
    3.70
     traps
    2.88
     trap
    2.53
     mistakes
    2.52
     pit
    2.41
     Traps
    2.31
     Pit
    2.17
    pit
    2.08
     avoid
    2.05
    Pit
    2.00
    Activations Density 0.129%

    No Known Activations