© 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. 83703
    Prev
    Next
    INDEX
    Explanations

    fon or sulfon

    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
    -2.47
    呖
    -2.44
    
    -2.41
     you
    -2.39
    锜
    -2.31
    乆
    -2.27
     хорошая
    -2.23
    樯
    -2.20
    仉
    -2.17
     comodo
    -2.16
    POSITIVE LOGITS
    л
    2.59
    𖣔
    2.36
    暃
    2.34
    Our
    2.31
    ſand
    2.22
     moody
    2.22
     emergence
    2.16
     erste
    2.13
     You
    2.13
    伝統
    2.09
    Activations Density 0.005%

    No Known Activations