© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5371
    Prev
    Next
    INDEX
    Explanations

    continual and continuous concepts

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

    constant, continuous, ongoing

    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
    дование
    0.40
     glBindTexture
    0.38
    addContainerGap
    0.37
     بخير
    0.36
    ್ರಾ
    0.35
    ర్కొ
    0.33
    糙
    0.33
    locationY
    0.32
    ေါ
    0.32
    ,"@
    0.32
    POSITIVE LOGITS
     continuous
    4.47
    continuous
    4.31
    Continuous
    4.28
     Continuous
    4.22
     continuously
    4.16
     continual
    3.69
     sürekli
    3.69
     continuamente
    3.58
     continually
    3.52
     kontinuier
    3.47
    Activations Density 0.373%

    No Known Activations