© 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. 910
    Prev
    Next
    INDEX
    Explanations

    during a period or event

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

    during events and periods

    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
     USING
    0.35
    諄
    0.35
     EXISTING
    0.34
    现在的
    0.33
     Date
    0.32
     Where
    0.32
    Date
    0.32
     <<-
    0.32
     essendo
    0.32
     ljudi
    0.31
    POSITIVE LOGITS
     Ramadan
    0.61
     pregnancy
    0.58
     downtime
    0.58
     rehearsals
    0.58
     halftime
    0.56
     filming
    0.54
     lockdown
    0.54
     deliberations
    0.53
     adolescence
    0.51
    pregnancy
    0.50
    Activations Density 0.348%

    No Known Activations