© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8673
    Prev
    Next
    INDEX
    Explanations

    Malta and Maltese topics

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

    Malta

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Asheville
    0.46
    〞
    0.45
    ￣
    0.40
     হলো
    0.40
    }">${
    0.40
    ாக
    0.39
    anceled
    0.39
    }".
    0.38
     Indones
    0.38
     أيض
    0.37
    POSITIVE LOGITS
     Malta
    2.13
     Maltese
    2.02
     Valletta
    1.80
    Ħ
    1.21
     malt
    1.05
    1.04
     Malt
    1.03
    malt
    1.02
    ħ
    0.99
     għ
    0.93
    Activations Density 0.058%

    No Known Activations