© 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. 81240
    Prev
    Next
    INDEX
    Explanations

    iced tea, milk tea, shakes

    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
    owitz
    -0.78
     noop
    -0.76
     chili
    -0.75
     mahi
    -0.72
     SOCK
    -0.72
     sardines
    -0.71
     Tyne
    -0.69
     nasi
    -0.68
    Sauce
    -0.68
     Thermostat
    -0.68
    POSITIVE LOGITS
     tea
    1.53
     Tea
    1.32
    Tea
    1.27
    tea
    1.26
     чай
    1.09
     pearls
    1.09
     teas
    1.09
     tapioca
    1.08
     Pearls
    1.06
     pearl
    1.05
    Activations Density 0.009%

    No Known Activations