© 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. 114125
    Prev
    Next
    INDEX
    Explanations

    Ha followed by names or place names

    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
    which
    -3.50
    鹮
    -2.86
     wich
    -2.70
     Reisedaten
    -2.67
    udsman
    -2.66
    𖤍
    -2.59
    仃
    -2.58
    鲧
    -2.58
    vably
    -2.53
    ᨁ
    -2.53
    POSITIVE LOGITS
     intrigue
    2.56
    퐼
    2.47
     untold
    2.27
     "(
    2.23
    
    2.20
     indisputable
    2.17
     ナビ
    2.17
    )：
    2.16
    たちも
    2.14
    他想
    2.13
    Activations Density 0.003%

    No Known Activations