© 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. 2831
    Prev
    Next
    INDEX
    Explanations

    colors

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

    colors

    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
    膺
    0.45
    ernacle
    0.39
    ลล์
    0.38
    徙
    0.38
    夻
    0.37
    ᕈ
    0.37
     জিৎ
    0.36
    嫒
    0.36
    Coref
    0.35
    ဖို့
    0.35
    POSITIVE LOGITS
     yellow
    3.31
     purple
    3.28
     blue
    3.27
    黄色
    3.03
    蓝色
    2.98
     orange
    2.97
     pink
    2.88
     magenta
    2.88
    紫色
    2.86
     yellowish
    2.83
    Activations Density 0.705%

    No Known Activations