© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1955
    Prev
    Next
    INDEX
    Explanations

    HTML tags and properties

    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
    McK
    0.38
    埤
    0.38
    簑
    0.38
    鯽
    0.36
    閪
    0.36
    壇
    0.36
    坵
    0.36
    ลูกค้า
    0.35
    敎
    0.35
    כּ
    0.35
    POSITIVE LOGITS
     left
    0.44
     >
    0.43
     LEFT
    0.42
     <
    0.40
     expand
    0.39
     colspan
    0.39
     rowspan
    0.39
     minValue
    0.38
     setActive
    0.38
     maxHeight
    0.38
    Activations Density 0.022%

    No Known Activations