© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6918
    Prev
    Next
    INDEX
    Explanations

    Chicago and Illinois locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Tenerife
    1.39
     Telf
    1.39
    ཚ
    1.31
     Sheikh
    1.31
    Colombo
    1.30
     Bahrain
    1.29
     ناک
    1.28
     Tobago
    1.25
    陀
    1.24
     Bodrum
    1.24
    POSITIVE LOGITS
    waukee
    2.16
     Racine
    2.04
    Wisconsin
    2.02
    Illinois
    2.01
    INOIS
    1.98
     ILLINOIS
    1.92
     Rockford
    1.90
     Wabash
    1.88
     Illinois
    1.85
    CHICAGO
    1.79
    Activations Density 0.241%

    No Known Activations