© 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. 30069
    Prev
    Next
    INDEX
    Explanations

    Eff

    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
     joyous
    -0.79
    がよく
    -0.74
     partners
    -0.73
    zesi
    -0.71
    Dez
    -0.70
    perfectly
    -0.70
    ături
    -0.69
    mainly
    -0.68
    GtkWidget
    -0.68
    ckel
    -0.67
    POSITIVE LOGITS
     Eff
    1.54
    eff
    1.50
     eff
    1.41
    Eff
    1.31
     Ef
    1.23
     EFF
    1.18
     ефек
    1.05
     Effec
    1.01
    ef
    0.96
    Ef
    0.94
    Activations Density 0.028%

    No Known Activations