© 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. 17623
    Prev
    Next
    INDEX
    Explanations

    bucket, scoop, shovel, fill

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

    bucket container scoop shovel

    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
    Bud
    0.48
    buds
    0.46
    jewelry
    0.45
    鮨
    0.43
     jewellery
    0.40
    alcool
    0.40
    bud
    0.40
     Buds
    0.39
    ジュエリー
    0.39
     jewelry
    0.38
    POSITIVE LOGITS
     bucket
    3.08
     Bucket
    2.95
     buckets
    2.94
    bucket
    2.81
    Bucket
    2.80
    buckets
    2.47
    桶
    2.16
     scoop
    1.97
     scoops
    1.88
     shovel
    1.85
    Activations Density 0.089%

    No Known Activations