© 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. 4763
    Prev
    Next
    INDEX
    Explanations

    Dur prefix and variations

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

    durability and duration

    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
    深度
    0.40
    帥
    0.38
     Worse
    0.37
    ")],
    0.37
    帅
    0.37
     ficam
    0.36
    想像
    0.36
    仔
    0.36
     reiv
    0.36
     dimes
    0.36
    POSITIVE LOGITS
    Dur
    0.90
     dur
    0.89
     Dur
    0.88
     DUR
    0.88
    dur
    0.77
     Dura
    0.71
     durability
    0.68
     dure
    0.62
     Duran
    0.62
     durable
    0.59
    Activations Density 0.016%

    No Known Activations