© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7790
    Prev
    Next
    INDEX
    Explanations

    summer months

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

    summer and winter months

    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
     celebrado
    0.45
     Minute
    0.44
    celebr
    0.41
     Moment
    0.40
     દિવસે
    0.40
     ત્યારે
    0.39
    取り組み
    0.39
    녠
    0.39
     Year
    0.38
    プレゼント
    0.38
    POSITIVE LOGITS
     months
    1.46
    months
    1.31
    Months
    1.16
     meses
    1.15
     Months
    1.15
     месяцев
    1.13
     maanden
    1.06
     miesięcy
    0.98
     महीनों
    0.95
     solstice
    0.95
    Activations Density 0.051%

    No Known Activations