© 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. 2669
    Prev
    Next
    INDEX
    Explanations

    fruits

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

    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
    좔
    0.49
    啸
    0.47
    悍
    0.46
     اولمپ
    0.45
    绻
    0.44
    缜
    0.42
    俦
    0.42
     INSEE
    0.41
    嘯
    0.41
    खास्त
    0.40
    POSITIVE LOGITS
     fruit
    3.02
     fruits
    2.88
     apples
    2.77
     strawberries
    2.73
    fruit
    2.64
     peaches
    2.64
    水果
    2.64
     tomatoes
    2.61
     frutas
    2.59
     Fruit
    2.58
    Activations Density 0.546%

    No Known Activations