© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3625
    Prev
    Next
    INDEX
    Explanations

    Auto model loading and locale

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    r
    0.75
    י
    0.72
    n
    0.71
    ,
    0.69
    라
    0.66
    ק
    0.64
    t
    0.63
    .
    0.63
    ש
    0.63
    ร
    0.62
    POSITIVE LOGITS
     করিয়াছিল
    0.64
     করিয়াছে
    0.57
    ，“
    0.55
    」，
    0.54
    ’)
    0.53
     Suu
    0.53
    
    0.52
    ]，
    0.52
     for
    0.51
    मैंने
    0.50
    Activations Density 0.002%

    No Known Activations