© 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. 10-GEMMASCOPE-RES-131K
    7. 83705
    Prev
    Next
    INDEX
    Explanations

    instead

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     also
    -1.95
     however
    -1.74
     azonban
    -1.55
    感じです
    -1.50
     both
    -1.50
     therefore
    -1.49
     również
    -1.45
    梆
    -1.41
    もあった
    -1.40
     thus
    -1.38
    POSITIVE LOGITS
     will
    1.98
     вместо
    1.81
     instead
    1.73
     Instead
    1.66
    Instead
    1.55
    instead
    1.53
     zamiast
    1.52
     istället
    1.50
    而是
    1.45
    或
    1.34
    Activations Density 0.020%

    No Known Activations