© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12651
    Prev
    Next
    INDEX
    Explanations

    historical computing and data processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    โลก
    0.43
     inducing
    0.40
     העולם
    0.40
    inducing
    0.40
    
    0.40
    PTV
    0.40
     frères
    0.40
     cappuccino
    0.40
     ß
    0.39
    ളി
    0.38
    POSITIVE LOGITS
     punched
    0.64
     punch
    0.59
     cards
    0.58
     card
    0.57
     paragraph
    0.57
     reels
    0.54
     punches
    0.54
     paragraphs
    0.53
     trending
    0.52
     Control
    0.51
    Activations Density 0.061%

    No Known Activations