© 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. 6714
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     after
    -1.72
     and
    -1.71
     pavillon
    -1.69
    tą
    -1.65
     poulet
    -1.62
    ſam
    -1.61
    arbol
    -1.60
    Etimología
    -1.60
     josé
    -1.59
     with
    -1.55
    POSITIVE LOGITS
     decidedly
    2.48
     remarkably
    2.27
     extremely
    2.19
     exceedingly
    2.19
     largely
    2.17
     VERY
    2.13
     vastly
    2.13
     
    2.08
     strikingly
    2.08
     unbelievably
    2.05
    Activations Density 0.004%

    No Known Activations