© 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. 22-GEMMASCOPE-RES-131K
    7. 127790
    Prev
    Next
    INDEX
    Explanations

    De Ruyter medal

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     their
    -1.82
     what
    -1.45
     Every
    -1.40
    وفر
    -1.35
     every
    -1.33
    
    -1.31
     find
    -1.26
    骓
    -1.25
     From
    -1.24
     have
    -1.22
    POSITIVE LOGITS
     of
    1.59
     delightfully
    1.37
     bearbeitet
    1.31
    かというと
    1.28
     wondrous
    1.27
     unquestion
    1.25
     intrigu
    1.23
     strikingly
    1.22
     diversos
    1.20
     begrenzt
    1.20
    Activations Density 0.000%

    No Known Activations