© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47474
    Prev
    Next
    INDEX
    Explanations

    seller and vendor

    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
    Not in Any Lists

    No Comments

    Negative Logits
     prénom
    -0.73
     cAMP
    -0.71
     Prometheus
    -0.70
    viewing
    -0.70
    cii
    -0.69
    muting
    -0.69
    Brittany
    -0.68
    řel
    -0.68
    cleros
    -0.67
    Convenience
    -0.67
    POSITIVE LOGITS
    륭
    0.82
     seller
    0.76
    eradish
    0.75
    ıllı
    0.74
    ()));
    0.73
    ٌ
    0.72
     Earle
    0.72
    Headline
    0.71
     Ojo
    0.70
     theoretical
    0.69
    Activations Density 0.019%

    No Known Activations