© 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. 7894
    Prev
    Next
    INDEX
    Explanations

    multiple languages and conjunctions

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

    japanese greetings and responses

    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
     우리나라
    0.71
     korea
    0.67
     kalau
    0.65
     Kalau
    0.64
     Japon
    0.64
     괜
    0.63
     แถม
    0.61
     こんな
    0.60
     고민
    0.60
     쭉
    0.60
    POSITIVE LOGITS
    および
    0.93
    人々
    0.82
    または
    0.80
    하십시오
    0.75
    电子邮件
    0.75
    に基づいて
    0.73
    ​​
    0.72
     および
    0.72
    その他の
    0.71
    少なくとも
    0.71
    Activations Density 0.016%

    No Known Activations