© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9519
    Prev
    Next
    INDEX
    Explanations

    verb followed by the

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

    prepositions followed by the

    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_40_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
     পত্রিকাটি
    0.45
     나머지
    0.44
     দলটি
    0.43
    ওই
    0.42
    のお店
    0.41
     ҳу
    0.40
     روستا
    0.39
    該
    0.39
     나머
    0.39
    获奖
    0.39
    POSITIVE LOGITS
     দ্য
    0.52
     the
    0.48
     either
    0.46
    either
    0.43
    various
    0.43
     The
    0.43
     various
    0.43
    the
    0.43
     tzw
    0.42
    经典的
    0.41
    Activations Density 0.376%

    No Known Activations