© 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. 17547
    Prev
    Next
    INDEX
    Explanations

    execution or potential execution

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

    execution

    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
    鰓
    0.39
    र्नल
    0.39
     erit
    0.37
     Sorrent
    0.37
    কবি
    0.37
     সনদ
    0.36
    mathml
    0.36
     কাদ
    0.36
     সাও
    0.36
    蒾
    0.35
    POSITIVE LOGITS
     execution
    4.59
     Execution
    4.38
     execute
    4.34
    execution
    4.19
    Execution
    4.16
    执行
    4.13
     executed
    4.06
     executions
    4.06
     executing
    4.03
    execute
    4.00
    Activations Density 0.186%

    No Known Activations