© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 615
    Prev
    Next
    INDEX
    Explanations

    drinks and beverages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     антенна
    0.74
    Inspection
    0.67
     ಬ್ಯಾ
    0.67
     ഭ
    0.66
     GridPane
    0.65
     XPath
    0.65
    蝗
    0.65
     век
    0.64
    褶
    0.64
     getpath
    0.63
    POSITIVE LOGITS
     drink
    3.79
     drinks
    3.72
     beverage
    3.70
     beverages
    3.69
    drink
    3.34
    drinks
    3.32
     Drinks
    3.28
     Drink
    3.27
     drank
    3.24
     drinking
    3.19
    Activations Density 2.073%

    No Known Activations