© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5305
    Prev
    Next
    INDEX
    Explanations

    Illinois

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

    illegal, illness, critical

    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
    祹
    0.44
    澼
    0.38
    үкт
    0.38
     टिश
    0.37
    Ձ
    0.36
    uyết
    0.35
    万元
    0.34
    ᐱ
    0.34
     கண்ணாடி
    0.33
    拚
    0.33
    POSITIVE LOGITS
     IL
    3.22
    IL
    3.13
     Il
    3.05
     il
    2.98
    Il
    2.91
    il
    2.88
     İl
    2.66
    イル
    2.61
     Иль
    2.59
    ил
    2.50
    Activations Density 0.197%

    No Known Activations