© 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. 38522
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and specific codes

    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
     our
    -1.80
    Хороший
    -1.80
     було
    -1.79
    when
    -1.77
    ’.
    -1.77
     those
    -1.76
    ’,
    -1.75
    D
    -1.70
    }
    -1.70
     some
    -1.70
    POSITIVE LOGITS
    岀
    1.87
     muitos
    1.80
    
    1.78
     lâng
    1.74
     alojamientos
    1.73
    饧
    1.72
     informaron
    1.70
     bocetos
    1.69
     primeiros
    1.66
     ingenieros
    1.66
    Activations Density 0.157%

    No Known Activations