© 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. 8341
    Prev
    Next
    INDEX
    Explanations

    duration in years months weeks

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

    years and 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
    বছ
    0.44
    情的
    0.42
    nms
    0.42
    挼
    0.41
     Tahun
    0.40
    年份
    0.40
    犇
    0.40
     Year
    0.40
    Huang
    0.40
     oportun
    0.39
    POSITIVE LOGITS
    +,
    0.42
     ক্রিয়া
    0.41
     wherein
    0.40
     hr
    0.39
    +)
    0.38
    +.
    0.38
     realm
    0.37
    +"
    0.37
    +}
    0.37
     Ио
    0.37
    Activations Density 0.002%

    No Known Activations