© 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. 64421
    Prev
    Next
    INDEX
    Explanations

    fast completion and quality

    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
     özellikle
    -1.16
    обзор
    -1.04
     jueves
    -1.04
    obut
    -1.02
    moiselle
    -1.02
    RAINE
    -0.99
    termilk
    -0.98
    ⫹
    -0.98
    (;;)
    -0.98
    terscotch
    -0.98
    POSITIVE LOGITS
     quality
    1.52
     subsequent
    1.24
     then
    1.23
     was
    1.07
     Затем
    1.06
    ި
    1.03
     никаких
    1.02
     time
    1.02
     thereafter
    1.02
     Quality
    1.01
    Activations Density 0.010%

    No Known Activations