© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110843
    Prev
    Next
    INDEX
    Explanations

    countless times

    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
     three
    -1.16
     two
    -1.04
     five
    -1.00
     four
    -0.99
    Some
    -0.93
     بیشتری
    -0.93
     Some
    -0.91
     moderately
    -0.90
     unusually
    -0.90
     it
    -0.88
    POSITIVE LOGITS
     countless
    4.44
    无数
    3.23
     innumerable
    3.22
     myriad
    2.91
     endless
    2.86
     infinite
    2.78
     innumer
    2.75
     numerous
    2.64
     thousands
    2.44
    numer
    2.44
    Activations Density 0.093%

    No Known Activations