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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45852
    Prev
    Next
    INDEX
    Explanations

    months of the year

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

    months and dates

    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_31_width_262k_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
     Μ
    0.74
    ї
    0.72
     Ζ
    0.70
     Γ
    0.67
     จ
    0.66
     ਰ
    0.66
     ก
    0.66
     ล
    0.66
    י
    0.65
     ด
    0.65
    POSITIVE LOGITS
     ноябре
    0.77
     меся
    0.61
     فبراير
    0.57
    下旬
    0.57
     месяца
    0.57
     كلام
    0.55
    يطان
    0.55
    سمبر
    0.54
     يُ
    0.54
    Кла
    0.54
    Activations Density 0.066%

    No Known Activations