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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 3711
    Prev
    Next
    INDEX
    Explanations

    German articles followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    Œ
    1.58
    lük
    1.55
    ท้าย
    1.55
    бавить
    1.54
    мой
    1.52
    valueChanged
    1.51
    芋
    1.51
    áč
    1.48
    тельностью
    1.48
     réessayer
    1.46
    POSITIVE LOGITS
    nict
    1.37
    んじゃない
    1.21
    platform
    1.14
    means
    1.09
     incluyendo
    1.07
     sentiment
    1.07
    gea
    1.07
     appare
    1.06
     arrangement
    1.04
    ovanje
    1.03
    Activations Density 0.028%

    No Known Activations