© 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. 83962
    Prev
    Next
    INDEX
    Explanations

    sarcasm and satire

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AND
    -1.44
     They
    -1.43
    音が
    -1.42
    м
    -1.40
     reduce
    -1.39
     startled
    -1.38
    AB
    -1.38
    begin
    -1.37
     from
    -1.36
    ༛
    -1.36
    POSITIVE LOGITS
     professionelle
    1.48
     Noviembre
    1.41
     acuerdos
    1.41
     ameryka
    1.40
     contribution
    1.39
    躰
    1.38
     новым
    1.35
     рисунки
    1.34
    把自己
    1.34
    mathrm
    1.34
    Activations Density 0.016%

    No Known Activations