© 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. 503
    Prev
    Next
    INDEX
    Explanations

    get my

    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
    Not in Any Lists

    No Comments

    Negative Logits
    5
    1.27
    4
    1.27
    ка
    1.10
    0
    1.09
    6
    1.05
    2
    0.91
    3
    0.89
    도
    0.86
    も
    0.85
    ту
    0.80
    POSITIVE LOGITS
     on
    0.82
    tting
    0.67
     It
    0.64
    υτό
    0.61
    ਾਈ
    0.59
     Plants
    0.58
    aways
    0.58
     up
    0.57
    alers
    0.57
    璺
    0.57
    Activations Density 5.043%

    No Known Activations