© 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. 22-GEMMASCOPE-RES-131K
    7. 64450
    Prev
    Next
    INDEX
    Explanations

    legal conviction or guilty verdict

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     economic
    -0.87
     choose
    -0.85
    肥料
    -0.84
     information
    -0.83
     without
    -0.82
     budget
    -0.81
    把手
    -0.81
     important
    -0.79
    fillStyle
    -0.76
     money
    -0.76
    POSITIVE LOGITS
     délais
    0.97
     huiles
    0.96
     quantités
    0.94
    ByUrl
    0.92
     investissements
    0.91
     réduire
    0.88
    URN
    0.88
    Entire
    0.87
    🦶
    0.87
    lein
    0.83
    Activations Density 0.055%

    No Known Activations