© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13335
    Prev
    Next
    INDEX
    Explanations

    January and dates

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

    January and new year

    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_16k_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
     wildflowers
    0.42
    March
    0.41
     धारणा
    0.41
    蚩
    0.40
     springtime
    0.40
    春秋
    0.39
     March
    0.39
    秋
    0.39
     maart
    0.39
    兴奋
    0.39
    POSITIVE LOGITS
     JANUARY
    0.95
     January
    0.94
    January
    0.94
     Januari
    0.91
    新年
    0.90
     janvier
    0.89
    JAN
    0.89
     जनवरी
    0.87
     JAN
    0.84
     jan
    0.83
    Activations Density 0.172%

    No Known Activations