© 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. 91728
    Prev
    Next
    INDEX
    Explanations

    loading states and api data

    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
     profondément
    -1.00
    Acciones
    -0.99
    btnLogin
    -0.98
    Akira
    -0.98
    UrlHelper
    -0.96
    Ян
    -0.94
    NewUrl
    -0.93
    Оп
    -0.93
     hamil
    -0.92
    Олег
    -0.92
    POSITIVE LOGITS
     show
    1.48
     loading
    1.44
     open
    1.34
     is
    1.24
    show
    1.23
     visible
    1.20
     selected
    1.17
    loading
    1.16
     error
    1.16
    is
    1.16
    Activations Density 0.006%

    No Known Activations