© 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. 2736
    Prev
    Next
    INDEX
    Explanations

    aromas and sensory qualities

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

    scents and smells

    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
     eyewitness
    0.49
    숀
    0.45
     синх
    0.45
    盱
    0.45
    쑤
    0.43
     நிய
    0.43
    ิจ
    0.43
    岌
    0.42
    ద్దా
    0.42
    簽證
    0.41
    POSITIVE LOGITS
     aroma
    2.39
     aromas
    2.38
     scents
    2.25
     scent
    2.17
     fragrance
    2.16
     fragrances
    2.09
     аромат
    2.08
     smells
    2.05
    香り
    2.02
     aromatic
    2.00
    Activations Density 0.342%

    No Known Activations