© 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. 10-GEMMASCOPE-RES-131K
    7. 68648
    Prev
    Next
    INDEX
    Explanations

    reprimanded or criticized

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     With
    -1.41
     свою
    -1.35
     assist
    -1.32
     Hinblick
    -1.30
     zahlreiche
    -1.29
    (
    -1.29
     Einzelnen
    -1.28
     daring
    -1.27
    www
    -1.25
    ช่วย
    -1.23
    POSITIVE LOGITS
     producenta
    1.51
     mismas
    1.51
    ܖ
    1.51
     penghargaan
    1.49
    NEYS
    1.49
     misma
    1.47
     bicchiere
    1.45
    ſſel
    1.41
    次は
    1.41
     белые
    1.39
    Activations Density 0.031%

    No Known Activations