© 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. 31-GEMMASCOPE-2-RES-262K
    7. 247581
    Prev
    Next
    INDEX
    Explanations

    Prepositions and articles in Romance and Germanic languages

    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_31_width_262k_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
    the
    0.43
     heeft
    0.43
    如果
    0.41
     έχει
    0.40
    使
    0.40
    ถ้า
    0.38
     在
    0.37
    这是
    0.37
    確認
    0.36
     ihe
    0.36
    POSITIVE LOGITS
    ire
    0.32
    ला
    0.31
     berkaitan
    0.30
    ли
    0.30
    만이
    0.30
    اک
    0.30
     unidades
    0.29
     periphery
    0.29
    ندی
    0.29
     sorely
    0.28
    Activations Density 0.006%

    No Known Activations