© 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. 8078
    Prev
    Next
    INDEX
    Explanations

    waste and discarded items

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

    waste, byproducts, leftovers

    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
    螅
    0.43
    面对
    0.40
    समोर
    0.39
    面對
    0.39
     ታ
    0.38
     редакти
    0.38
     सश
    0.36
    远程
    0.36
     เง
    0.36
     पग
    0.36
    POSITIVE LOGITS
     waste
    2.34
     discarded
    2.31
    废
    2.20
    waste
    2.19
    廢
    2.16
     Waste
    2.09
     déchets
    2.09
    Waste
    2.08
     leftovers
    2.06
     wastes
    2.05
    Activations Density 0.231%

    No Known Activations