© 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-262K
    7. 180140
    Prev
    Next
    INDEX
    Explanations

    IMDb conversation League eating

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

    countries, cities, and security protocols

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     or
    0.57
     Circ
    0.47
     Sub
    0.47
     Pent
    0.46
    −
    0.46
     Exc
    0.45
     Cal
    0.45
     evergreen
    0.45
     Tract
    0.45
     Popul
    0.44
    POSITIVE LOGITS
     glorify
    0.47
     قيم
    0.46
     dienen
    0.45
     optimizations
    0.45
     enqueue
    0.44
    솎
    0.44
    იღ
    0.44
     marchandises
    0.43
    哟
    0.43
     degeneracy
    0.42
    Activations Density 0.001%

    No Known Activations