Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1848
    Prev
    Next
    INDEX
    Explanations

    expressions of amusement and happiness

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

    positive emojis and punctuation

    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
    सुद्धा
    0.32
    vorschau
    0.31
     creditor
    0.29
    ביע
    0.29
    ही
    0.27
     असलेला
    0.27
    তিপ
    0.27
    ጹ
    0.27
    شاعرانه
    0.27
     affix
    0.26
    POSITIVE LOGITS
     hehe
    0.66
     ㅋㅋ
    0.62
     😉
    0.59
     hahaha
    0.59
     ㅎㅎ
    0.58
     haha
    0.58
     lol
    0.57
     ;)
    0.57
     😂
    0.55
     😀
    0.55
    Activations Density 0.221%

    No Known Activations