© 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. 38420
    Prev
    Next
    INDEX
    Explanations

    Hyper, Q, Background, Prote, Centers

    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
     Doesn
    -1.65
     "
    -1.64
     большин
    -1.63
     verursacht
    -1.63
     beinahe
    -1.50
     Maintaining
    -1.49
     gänzlich
    -1.49
     Various
    -1.49
    putan
    -1.48
     allmäh
    -1.48
    POSITIVE LOGITS
    雠
    1.70
     prestation
    1.70
    帏
    1.67
    我們
    1.67
    <td>
    1.63
    ريكية
    1.54
     своих
    1.53
    foi
    1.52
     炖
    1.49
     variabel
    1.49
    Activations Density 0.000%

    No Known Activations