© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15443
    Prev
    Next
    INDEX
    Explanations

    phrases following common prepositions or determiners

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

    titles of books or songs

    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_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
     معمولی
    0.46
    யா
    0.39
     camels
    0.38
    駱
    0.37
     camshaft
    0.37
    艘
    0.37
    ляет
    0.37
     litmus
    0.37
     gstlal
    0.37
    柯
    0.37
    POSITIVE LOGITS
    resi
    0.36
     ৭৮
    0.34
     '{
    0.33
    ord
    0.33
    を表
    0.33
    authorised
    0.32
    (\{
    0.32
    reso
    0.32
    。『
    0.32
    accepted
    0.31
    Activations Density 0.109%

    No Known Activations