© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49416
    Prev
    Next
    INDEX
    Explanations

    clients, Q&A

    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
    cookie
    -0.88
     tričko
    -0.84
    allergenic
    -0.81
     لحظه
    -0.81
    évaluation
    -0.81
    Παραπομπές
    -0.81
     everything
    -0.78
    其次
    -0.78
     apologise
    -0.77
    ké
    -0.77
    POSITIVE LOGITS
     clients
    0.97
     ._
    0.96
     widely
    0.95
     Plage
    0.93
     Nuova
    0.86
     GTI
    0.86
    >*
    0.85
    客户端
    0.85
     exporters
    0.84
     &'
    0.84
    Activations Density 0.008%

    No Known Activations