© 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. 84301
    Prev
    Next
    INDEX
    Explanations

    image files and icons

    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
    Jesus
    -0.70
    規劃
    -0.69
    台北
    -0.68
    ₿
    -0.67
     polynomials
    -0.67
    Examples
    -0.67
     MongoDB
    -0.66
    leyici
    -0.66
     autobiography
    -0.65
    Businesses
    -0.65
    POSITIVE LOGITS
     images
    1.95
     image
    1.80
     img
    1.57
     icon
    1.55
     icons
    1.53
    images
    1.49
     Images
    1.44
     gif
    1.43
     이미지
    1.38
     Image
    1.36
    Activations Density 0.052%

    No Known Activations