© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    It followed by verb

    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
     mélanger
    -1.06
     rapor
    -1.05
     iub
    -1.02
     pomi
    -0.98
     gato
    -0.96
     dégust
    -0.96
     zove
    -0.95
     habet
    -0.93
     ouver
    -0.93
    zzet
    -0.92
    POSITIVE LOGITS
     would
    2.17
     remains
    1.29
     all
    1.24
     remain
    1.18
     sería
    1.15
     is
    1.13
     was
    1.06
     sarebbe
    1.05
     seems
    1.05
     may
    1.05
    Activations Density 0.038%

    No Known Activations