© 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. 58058
    Prev
    Next
    INDEX
    Explanations

    prepositions or common following 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
    茈
    -1.61
    
    -1.48
     degrés
    -1.45
     canaux
    -1.40
     diriger
    -1.40
     ebbe
    -1.38
     ieri
    -1.37
    苤
    -1.37
     cœurs
    -1.37
     catég
    -1.36
    POSITIVE LOGITS
     to
    2.05
     which
    1.77
     all
    1.73
     as
    1.71
     will
    1.65
     it
    1.55
     every
    1.55
     each
    1.52
     before
    1.49
     through
    1.48
    Activations Density 1.122%

    No Known Activations