© 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. 60556
    Prev
    Next
    INDEX
    Explanations

    hundreds of counties

    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
     twelve
    -1.18
     fifteen
    -1.16
     fourteen
    -1.15
     sixteen
    -1.08
     eight
    -1.05
     ten
    -1.03
     thirteen
    -0.98
     eleven
    -0.96
    Twelve
    -0.95
     seventeen
    -0.95
    POSITIVE LOGITS
     hundreds
    2.14
    三百
    2.06
    Hundreds
    1.98
    hundreds
    1.97
    二百
    1.76
     Hundreds
    1.73
    数百
    1.56
     hundred
    1.52
    hundred
    1.47
     cientos
    1.43
    Activations Density 0.436%

    No Known Activations