© 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. 79511
    Prev
    Next
    INDEX
    Explanations

    professional rodeo

    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
    Sonic
    -0.81
    이고
    -0.77
     conservatory
    -0.73
     Consideration
    -0.70
    eramente
    -0.69
    nější
    -0.69
     harps
    -0.68
     hatchback
    -0.68
     choral
    -0.68
     SPD
    -0.66
    POSITIVE LOGITS
     bull
    1.41
    bull
    1.27
     bulls
    1.20
     Bull
    1.13
    Bull
    1.01
     rider
    0.96
     BULL
    0.94
     ride
    0.92
     bovine
    0.91
     arena
    0.88
    Activations Density 0.015%

    No Known Activations