© 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. 3530
    Prev
    Next
    INDEX
    Explanations

    ECU or Detroit

    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
     examines
    -0.67
    olarmente
    -0.66
     refrigeration
    -0.66
     Revisited
    -0.65
    アカウント
    -0.65
    цева
    -0.64
     météo
    -0.63
    讨论
    -0.63
    skirt
    -0.63
     urządzenia
    -0.62
    POSITIVE LOGITS
    Detroit
    1.15
     Detroit
    1.08
     Ecu
    1.05
     ECU
    1.02
    ECU
    0.96
    ciamento
    0.93
    DET
    0.91
     DET
    0.87
     ecu
    0.83
     chil
    0.82
    Activations Density 0.007%

    No Known Activations