© 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. 83660
    Prev
    Next
    INDEX
    Explanations

    trade tariffs or duties

    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
    鵟
    -3.06
    蟜
    -2.86
    寕
    -2.84
     撮っ
    -2.69
    ⢧
    -2.63
    蹓
    -2.58
    蟶
    -2.55
    
    -2.52
    ޏ
    -2.44
    ۠
    -2.44
    POSITIVE LOGITS
    .
    3.41
     
    3.22
    A
    2.84
    S
    2.80
    e
    2.72
    to
    2.64
    P
    2.59
    H
    2.58
    V
    2.52
    F
    2.47
    Activations Density 0.003%

    No Known Activations