© 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. 2649
    Prev
    Next
    INDEX
    Explanations

    months and days

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

    placeholders in formal communication

    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
     [...]
    0.46
    ­
    0.43
    
    0.40
     unittest
    0.38
    haus
    0.36
     ژان
    0.36
     […]
    0.36
     crowning
    0.36
    ম্‌
    0.36
    ुलिस
    0.35
    POSITIVE LOGITS
     ,
    1.92
     ，
    1.64
     (,
    1.52
     ،
    1.48
     (),
    1.42
     ).
    1.41
     .,
    1.39
     ),
    1.38
     ,"
    1.33
     )
    1.32
    Activations Density 0.877%

    No Known Activations