© 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. 16261
    Prev
    Next
    INDEX
    Explanations

    listing provided courtesy of

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

    reduce emphasis on

    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
    胁
    0.45
    ビン
    0.45
     erster
    0.45
     outperforms
    0.44
    บาง
    0.42
     fortr
    0.41
    臼
    0.40
     ब्राउन
    0.40
    脛
    0.40
     त्यानुसार
    0.40
    POSITIVE LOGITS
     加工
    0.47
    മാക്കി
    0.46
     nuestras
    0.45
    Mayor
    0.45
     repost
    0.44
    lerimiz
    0.44
    keen
    0.44
    ческую
    0.44
     skeptical
    0.43
     Mayor
    0.43
    Activations Density 0.005%

    No Known Activations