© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 696
    Prev
    Next
    INDEX
    Explanations

    projects, movies, properties

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

    large language models

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    會
    1.10
    of
    1.05
     的
    0.98
    ED
    0.98
    与
    0.98
     è
    0.97
    在
    0.96
     på
    0.95
    IT
    0.95
    أ
    0.93
    POSITIVE LOGITS
     carbure
    1.09
    ווי
    1.07
    ת
    1.03
     dimensioni
    0.92
    תה
    0.89
    ຈັດສົ່ງ
    0.88
     can
    0.87
     Abelian
    0.87
    ח
    0.86
    ,_-
    0.86
    Activations Density 3.321%

    No Known Activations