© 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. 19913
    Prev
    Next
    INDEX
    Explanations

    books and calligraphic collections

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

    Turkey's population statistics

    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
     mary
    0.47
    ังก์ชัน
    0.46
     choose
    0.45
     WILLIAM
    0.44
    ๎
    0.43
     Martha
    0.42
     দ্বারা
    0.42
     помощью
    0.42
     свя
    0.42
     تقویت
    0.42
    POSITIVE LOGITS
     Parlamento
    0.51
     eski
    0.47
     ilk
    0.45
    dürü
    0.45
     지난해
    0.45
     yapılan
    0.44
     mücade
    0.44
    :'],
    0.44
     Nacional
    0.43
     hareket
    0.43
    Activations Density 0.002%

    No Known Activations