© 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. 40-GEMMASCOPE-2-RES-262K
    7. 26293
    Prev
    Next
    INDEX
    Explanations

    Malta and Maltese topics

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Asheville
    0.40
     revitalize
    0.39
    〞
    0.38
     হলো
    0.38
    ாக
    0.37
     නිෂ්
    0.37
    }">${
    0.37
    〟
    0.36
    }".
    0.36
    ということです
    0.36
    POSITIVE LOGITS
     Malta
    2.13
     Maltese
    2.03
     Valletta
    1.73
    Ħ
    1.20
     malt
    1.09
     Malt
    1.04
    1.01
    ħ
    1.00
    malt
    0.96
    ġ
    0.93
    Activations Density 0.007%

    No Known Activations