© 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. 106315
    Prev
    Next
    INDEX
    Explanations

    male first names followed by surname starts

    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
     bible
    -0.79
     hanger
    -0.77
     Jehovah
    -0.73
    τώ
    -0.71
    ummings
    -0.71
     Allah
    -0.71
     crucifix
    -0.70
     church
    -0.69
     working
    -0.68
    麺
    -0.68
    POSITIVE LOGITS
     preached
    1.05
    ЖА
    0.95
    hopping
    0.92
    useNewUrlParser
    0.89
     medarbe
    0.84
     gustar
    0.81
     desaf
    0.81
     финансо
    0.81
     véhic
    0.79
    mathematical
    0.79
    Activations Density 0.060%

    No Known Activations