© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8619
    Prev
    Next
    INDEX
    Explanations

    Malta and Maltese language

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ِد
    0.44
    鼾
    0.43
     correspondió
    0.43
    〞
    0.43
     conduce
    0.41
    آن
    0.41
    ِي
    0.41
    スナー
    0.41
     electrolytic
    0.40
    ตาล
    0.39
    POSITIVE LOGITS
     Malta
    1.87
     Maltese
    1.79
     Valletta
    1.66
    Ħ
    1.09
    0.97
    ħ
    0.92
     Malt
    0.87
     malt
    0.82
    ġ
    0.82
    għ
    0.80
    Activations Density 0.007%

    No Known Activations