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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2431
    Prev
    Next
    INDEX
    Explanations

    hosts television presenters

    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
     Relations
    -0.73
    ᑌ
    -0.72
    acqu
    -0.69
     مفت
    -0.69
     depiction
    -0.68
     Relationships
    -0.67
     longitudinally
    -0.67
     detection
    -0.66
    Relations
    -0.65
     对
    -0.65
    POSITIVE LOGITS
     presenters
    1.09
     presenter
    1.08
    presenter
    1.05
     hosting
    1.00
     Presenter
    0.99
    Presenter
    0.90
     MTV
    0.89
     hosts
    0.88
     resourceCulture
    0.86
     presenting
    0.85
    Activations Density 0.031%

    No Known Activations