© 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. 5368
    Prev
    Next
    INDEX
    Explanations

    February dates and events

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

    February, often with years

    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
    夏の
    0.73
     июле
    0.68
    秋
    0.68
     autumnal
    0.66
     pumpkin
    0.64
    Autumn
    0.64
     夏
    0.62
     autumn
    0.61
     Autumn
    0.61
     秋
    0.61
    POSITIVE LOGITS
     Feb
    3.02
    Feb
    2.95
    February
    2.94
     February
    2.92
    feb
    2.69
     FEBRUARY
    2.61
     feb
    2.59
     febru
    2.58
     february
    2.58
     февра
    2.56
    Activations Density 0.164%

    No Known Activations