© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11559
    Prev
    Next
    INDEX
    Explanations

    YouTube videos and creators

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

    YouTube video links and channels

    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
    Negative Logits
    文學
    0.52
     सकाळी
    0.47
     romanzo
    0.44
    dataIn
    0.44
    解釋
    0.43
     рома
    0.43
     ము
    0.43
     coastal
    0.42
     утром
    0.42
    읽
    0.42
    POSITIVE LOGITS
     YouTube
    1.37
    YouTube
    1.33
     youtube
    1.25
     Youtube
    1.23
    youtube
    1.15
     यूट्यूब
    1.13
    Youtube
    1.13
     유튜브
    1.08
     ইউটিউ
    1.02
     YouTuber
    0.98
    Activations Density 0.098%

    No Known Activations