© 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. 15374
    Prev
    Next
    INDEX
    Explanations

    plurality of patterns

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

    receiving user input and displaying output

    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
    ش
    0.49
     물
    0.46
    醗
    0.44
    ض
    0.44
     الغ
    0.43
     ँ
    0.43
     All
    0.42
     للب
    0.42
     Tho
    0.41
    払
    0.41
    POSITIVE LOGITS
    дентификаторы
    0.53
    didReceive
    0.49
    AccountId
    0.48
    версите
    0.48
     fintech
    0.48
    cassandra
    0.47
    েইলি
    0.46
    Телефон
    0.46
     plurality
    0.46
    Vertices
    0.44
    Activations Density 0.726%

    No Known Activations