© 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. 79431
    Prev
    Next
    INDEX
    Explanations

    buy medications online

    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
     HOMES
    -0.89
    mbros
    -0.87
    üte
    -0.84
     maintained
    -0.82
     handels
    -0.81
    terapia
    -0.77
     sociedade
    -0.77
     gelt
    -0.76
    ⁰
    -0.76
     gaben
    -0.75
    POSITIVE LOGITS
     online
    1.59
     Canada
    1.25
     Australia
    1.24
     cheap
    1.13
     USA
    1.13
     generic
    1.11
    generic
    1.06
    Australia
    1.01
     overnight
    1.01
     cheapest
    1.00
    Activations Density 0.021%

    No Known Activations