© 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. 60535
    Prev
    Next
    INDEX
    Explanations

    Ore, cookies, pipe, questions

    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
     postcards
    -0.91
    protect
    -0.83
    intellij
    -0.79
     scones
    -0.79
    dill
    -0.77
     Вт
    -0.77
     steaks
    -0.76
     産
    -0.75
    setCell
    -0.75
     protecting
    -0.75
    POSITIVE LOGITS
     sprinkles
    0.99
     colored
    0.96
     candies
    0.94
     Ore
    0.91
     jim
    0.91
     отверсти
    0.88
     Fun
    0.85
     themed
    0.85
    graham
    0.85
     setColor
    0.83
    Activations Density 0.018%

    No Known Activations