© 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. 16742
    Prev
    Next
    INDEX
    Explanations

    introducer followed by punctuation/structure

    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
     prédé
    -1.10
    vejec
    -1.09
     filós
    -1.09
    ceptar
    -1.09
     funktioner
    -1.08
     TÉ
    -1.05
    kese
    -1.05
     inginkan
    -1.05
     egens
    -1.05
     AÑOS
    -1.03
    POSITIVE LOGITS
     these
    1.42
    这些
    1.41
     and
    1.38
    這些
    1.35
    ijnt
    1.12
     These
    1.12
     этими
    1.12
     to
    1.11
     этих
    1.09
    ингл
    1.06
    Activations Density 0.006%

    No Known Activations