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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7940
    Prev
    Next
    INDEX
    Explanations

    words preceding taste

    np_acts-logits-general · gemini-2.5-flash-lite

    tastes of fruit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     FSC
    0.42
    બંધ
    0.37
     Navarro
    0.37
     Roshan
    0.35
     zlo
    0.35
     Johnson
    0.35
    ዶ
    0.35
     বন্দ
    0.35
     BSC
    0.35
    பிர
    0.34
    POSITIVE LOGITS
     taste
    4.50
    taste
    4.09
     Taste
    4.06
    Taste
    4.03
     tastes
    3.91
     tasted
    3.83
     맛
    3.47
     tasting
    3.42
     вку
    3.39
    맛
    3.33
    Activations Density 0.163%

    No Known Activations