© 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. 58239
    Prev
    Next
    INDEX
    Explanations

    interest, concern, anxiety about

    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
     jeszcze
    -1.51
    峮
    -1.48
    рий
    -1.46
    訁
    -1.46
    caj
    -1.44
     überprü
    -1.42
     beiden
    -1.42
    versations
    -1.37
    餐厅
    -1.37
     gått
    -1.35
    POSITIVE LOGITS
     in
    2.28
     by
    2.28
     about
    1.91
     know
    1.47
     there
    1.38
    0
    1.32
     for
    1.30
    我了
    1.28
     on
    1.27
     around
    1.21
    Activations Density 0.109%

    No Known Activations