© 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. 1984
    Prev
    Next
    INDEX
    Explanations

    male first names

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

    names of people

    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
     在
    0.12
     ถ้า
    0.11
     cStart
    0.11
     โรง
    0.11
    ```
    0.11
     ইত্যা
    0.11
     умолчанию
    0.11
    📢
    0.11
     యుద్ధ
    0.11
     useState
    0.11
    POSITIVE LOGITS
     Michael
    0.29
     Matthew
    0.28
     David
    0.27
     Kevin
    0.27
     Richard
    0.27
     Chris
    0.27
     James
    0.26
     Stephen
    0.26
     Jonathan
    0.26
     Peter
    0.26
    Activations Density 0.992%

    No Known Activations