© 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. 22547
    Prev
    Next
    INDEX
    Explanations

    Cynthia Chang, Cynthia L., Cynthia K

    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
     was
    -3.06
     они
    -2.70
     його
    -2.53
     Which
    -2.52
     it
    -2.50
     are
    -2.39
     algunas
    -2.39
    鬭
    -2.30
     itulah
    -2.30
     étrangères
    -2.27
    POSITIVE LOGITS
    之为
    2.42
    ب
    2.39
    ⡱
    2.33
    銫
    2.27
    ꦫ
    2.27
     demean
    2.27
    ⢪
    2.25
     इसे
    2.22
    ፨
    2.17
    kiyor
    2.16
    Activations Density 0.001%

    No Known Activations