© 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. 47120
    Prev
    Next
    INDEX
    Explanations

    religious denominational terms

    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
     Toilet
    -0.73
    댄
    -0.73
     Jesus
    -0.72
    )\}$
    -0.71
    做了
    -0.70
     Gospels
    -0.69
     Rasulullah
    -0.69
     rosso
    -0.68
    ennett
    -0.68
    部的
    -0.67
    POSITIVE LOGITS
    Calvin
    0.92
     Reformed
    0.87
     Calvin
    0.87
     Aruba
    0.84
     Mackay
    0.80
     OPC
    0.79
    onomy
    0.78
     antithesis
    0.77
     sphere
    0.77
     Ols
    0.75
    Activations Density 0.016%

    No Known Activations