© 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. 72351
    Prev
    Next
    INDEX
    Explanations

    scores and wins

    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
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -1.67
     duquel
    -1.61
    鐿
    -1.44
     are
    -1.36
    就得
    -1.36
     Divulgação
    -1.34
     fiind
    -1.30
     경우
    -1.30
    岀
    -1.29
     melap
    -1.28
    POSITIVE LOGITS
     vermutlich
    1.50
     прось
    1.30
     wußte
    1.27
     kurzen
    1.27
     พร้อม
    1.25
     orchestrated
    1.25
     faisait
    1.24
     möglichen
    1.23
     dunklen
    1.21
     kleinen
    1.19
    Activations Density 0.014%

    No Known Activations