© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8350
    Prev
    Next
    INDEX
    Explanations

    BMW Bavaria

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

    BMW and Bavaria

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     गुजरात
    0.57
    गुजरात
    0.54
     WV
    0.53
     Shreveport
    0.51
     গুজ
    0.48
     आंध्र
    0.47
    Gujarat
    0.46
    🖒
    0.46
     venezol
    0.46
    WV
    0.46
    POSITIVE LOGITS
    BMW
    1.23
     BMW
    1.23
     bmw
    1.20
     Bavaria
    1.13
     Bavarian
    1.12
     Munich
    1.07
     Bayern
    0.96
    Bayern
    0.94
     München
    0.93
     Bav
    0.93
    Activations Density 0.162%

    No Known Activations