© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9119
    Prev
    Next
    INDEX
    Explanations

    month or monthly time periods

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

    month names 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_40_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
     周
    0.54
    周
    0.51
    Monday
    0.44
    Zhou
    0.43
     ге
    0.41
     Thursday
    0.40
    Yesterday
    0.40
     Circum
    0.40
    当日
    0.40
    주
    0.40
    POSITIVE LOGITS
     month
    1.98
     monthly
    1.92
     Month
    1.80
    month
    1.76
    Month
    1.71
     Monthly
    1.69
     MONTH
    1.67
    Monthly
    1.66
    monthly
    1.65
     mês
    1.63
    Activations Density 0.386%

    No Known Activations