© 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. 34-GEMMASCOPE-RES-131K
    7. 56792
    Prev
    Next
    INDEX
    Explanations

    before roll / change namespace / module namespace

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    lés
    -0.79
    ARA
    -0.75
     addUser
    -0.72
     xong
    -0.70
    芪
    -0.69
    URS
    -0.69
     ghz
    -0.68
    шься
    -0.68
     Fredrik
    -0.67
     CATALOG
    -0.66
    POSITIVE LOGITS
    nun
    0.75
     nära
    0.72
    空的
    0.72
    Improved
    0.71
     Formosa
    0.69
     coopération
    0.69
     энерго
    0.69
     först
    0.69
     sky
    0.68
     högre
    0.68
    Activations Density 0.049%

    No Known Activations