© 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. 83676
    Prev
    Next
    INDEX
    Explanations

    can

    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
    為
    -1.34
    ASKET
    -1.31
     kvalitet
    -1.31
    ."
    -1.31
    шні
    -1.28
     時計
    -1.27
    
    -1.26
     設置
    -1.25
     rajut
    -1.25
    dámské
    -1.24
    POSITIVE LOGITS
    此事
    1.56
    EdgeInsets
    1.45
    ⬮
    1.44
     you
    1.43
     YOU
    1.41
    ⎙
    1.39
    
    1.38
    bcryptjs
    1.37
     should
    1.32
    倘
    1.30
    Activations Density 0.098%

    No Known Activations