© 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. 79428
    Prev
    Next
    INDEX
    Explanations

    performance metrics

    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
    pfn
    -0.81
    служ
    -0.76
     Pokies
    -0.76
    čili
    -0.73
     risol
    -0.72
     запас
    -0.71
    льника
    -0.71
    rý
    -0.71
    biť
    -0.70
     بشه
    -0.70
    POSITIVE LOGITS
     Expected
    1.05
     attempted
    1.02
     Attempt
    0.99
     Successful
    0.98
     metrics
    0.98
    attempt
    0.97
    Attempt
    0.94
     successful
    0.92
     FBref
    0.92
    successful
    0.90
    Activations Density 0.007%

    No Known Activations