© 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. 118528
    Prev
    Next
    INDEX
    Explanations

    url and type in ajax

    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
    elezo
    -0.88
     each
    -0.81
    =(
    -0.81
    Starting
    -0.79
    せい
    -0.78
    mlung
    -0.77
     affecting
    -0.76
     often
    -0.75
     about
    -0.75
     any
    -0.75
    POSITIVE LOGITS
     type
    1.77
    type
    1.60
     url
    1.55
    url
    1.47
     typu
    1.16
    TYPE
    1.14
     URL
    1.09
     Type
    1.08
     TYPE
    1.05
     URLs
    1.05
    Activations Density 0.006%

    No Known Activations