© 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. 58923
    Prev
    Next
    INDEX
    Explanations

    counter, bar, or island

    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
    binaan
    -0.83
    вий
    -0.79
     Median
    -0.79
     daisy
    -0.78
    doria
    -0.75
    bby
    -0.75
    满了
    -0.73
    filet
    -0.73
    NVIC
    -0.73
     hergestellt
    -0.73
    POSITIVE LOGITS
     counter
    2.34
     bar
    2.09
     stools
    1.97
     Counter
    1.94
    counter
    1.73
    Counter
    1.70
     stool
    1.62
     countertop
    1.58
     counters
    1.52
     COUNTER
    1.49
    Activations Density 0.009%

    No Known Activations