© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 857
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    _
    0.84
    ک
    0.70
    ки
    0.65
    س
    0.64
    ע
    0.60
    した
    0.59
     wśród
    0.59
     istraž
    0.59
     imprend
    0.57
    یر
    0.57
    POSITIVE LOGITS
     (
    0.61
    iest
    0.59
    isserie
    0.57
    iye
    0.54
    i
    0.54
    man
    0.52
    razione
    0.52
     detachable
    0.52
    etian
    0.51
     filet
    0.51
    Activations Density 1.531%

    No Known Activations