© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4820
    Prev
    Next
    INDEX
    Explanations

    foreign words followed by nouns

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

    utilizando diferentes tecnologías

    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
    Cela
    0.34
     /
    0.33
     無
    0.33
     avenir
    0.33
    dag
    0.31
    🌍
    0.31
     则
    0.30
    �
    0.30
     可能
    0.29
    Điều
    0.29
    POSITIVE LOGITS
     sebuah
    0.63
     sogenannten
    0.59
     sogenannte
    0.55
     знамени
    0.55
    著名的
    0.53
     крупней
    0.53
     मशहूर
    0.52
     একটি
    0.51
     একজন
    0.51
     tzv
    0.51
    Activations Density 0.012%

    No Known Activations