© 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. 58227
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common words

    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
    !
    -1.86
    1
    -1.84
    3
    -1.80
     There
    -1.80
     Saltar
    -1.77
     According
    -1.72
     will
    -1.66
    9
    -1.66
     each
    -1.62
     Obviously
    -1.62
    POSITIVE LOGITS
     vielen
    1.80
    鼉
    1.79
     pomocou
    1.76
     funktioniert
    1.70
     \$
    1.66
     maail
    1.60
    蛲
    1.60
     tijdens
    1.60
     $\$$
    1.60
     queridos
    1.59
    Activations Density 0.157%

    No Known Activations