© 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. 32659
    Prev
    Next
    INDEX
    Explanations

    UI views

    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
     telegram
    -0.85
     flexib
    -0.83
    telegraph
    -0.82
     場面
    -0.75
     dign
    -0.75
    ometr
    -0.75
     Willem
    -0.73
    楸
    -0.73
     شهرد
    -0.73
    ření
    -0.73
    POSITIVE LOGITS
    View
    1.55
     view
    1.45
     View
    1.28
     VIEW
    1.05
    view
    0.94
    VIEW
    0.89
     viewed
    0.88
     views
    0.85
    ></
    0.80
    Image
    0.78
    Activations Density 0.003%

    No Known Activations