© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    positive emotions and informal expressions

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

    informal slang

    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
     करीत
    0.55
    其它
    0.54
    镙
    0.54
     pertanto
    0.50
    部份
    0.49
     কতকগুলি
    0.48
     Folks
    0.47
    祗
    0.46
     proverbial
    0.46
    帐户
    0.46
    POSITIVE LOGITS
     lmao
    1.79
     idk
    1.66
    😭
    1.42
     tbh
    1.41
    😭😭
    1.32
    🥲
    1.26
     haha
    1.25
    🥺
    1.25
     lol
    1.20
     😂
    1.20
    Activations Density 0.126%

    No Known Activations