© 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. 41-GEMMASCOPE-2-RES-262K
    7. 1242
    Prev
    Next
    INDEX
    Explanations

    places that are cities or town names

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     élytres
    0.44
    និច
    0.44
    OLYBD
    0.41
    ាតុ
    0.40
    យៈ
    0.38
     échanc
    0.38
     fxaa
    0.38
     innumerable
    0.37
    <unused973>
    0.37
     auffi
    0.37
    POSITIVE LOGITS
     Hyderabad
    0.50
     Vila
    0.48
     Reykjavik
    0.48
     Pune
    0.47
     Din
    0.46
     Budapest
    0.45
     Port
    0.44
     Ahmedabad
    0.44
     An
    0.44
    in
    0.44
    Activations Density 0.004%

    No Known Activations