© 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. 37901
    Prev
    Next
    INDEX
    Explanations

    articles and nouns in Romance languages

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

    el + noun

    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
    아
    0.71
    a
    0.64
     السعودية
    0.62
    า
    0.62
     Lieferung
    0.61
    s
    0.61
     высокая
    0.60
     argentina
    0.59
     tecnica
    0.59
     μεγάλη
    0.59
    POSITIVE LOGITS
     próprio
    0.76
     peuple
    0.70
     discurso
    0.64
     concepto
    0.62
     mismo
    0.61
     lenguaje
    0.59
     koji
    0.59
     propósito
    0.59
    $
    0.59
     pequeño
    0.58
    Activations Density 0.017%

    No Known Activations