© 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. 22-GEMMASCOPE-RES-131K
    7. 127664
    Prev
    Next
    INDEX
    Explanations

    repeated numbers and characters

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    mayacak
    -1.10
    を目指す
    -1.10
     and
    -1.09
    compromising
    -1.06
     by
    -1.05
    phyla
    -1.03
     estaban
    -1.02
     sitesinde
    -1.02
    ਆਂ
    -1.02
    ೭
    -1.02
    POSITIVE LOGITS
    そして
    1.10
    である
    1.03
    などの
    1.02
    但却
    1.01
    どちらも
    1.00
     rasch
    0.98
     xxiv
    0.97
    OOOOOO
    0.96
    ですが
    0.96
    $
    0.94
    Activations Density 0.037%

    No Known Activations