© 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. 14826
    Prev
    Next
    INDEX
    Explanations

    effective, successful, most

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

    formal language and phrasing

    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
    𝑭
    0.49
    フェ
    0.47
     Федера
    0.47
    触摸
    0.46
    ার
    0.45
    监测
    0.45
     Андрей
    0.45
    았습니다
    0.45
    აციის
    0.44
    アク
    0.44
    POSITIVE LOGITS
     decor
    0.50
     domin
    0.44
     kett
    0.44
     hauteur
    0.44
     glor
    0.43
    ỡ
    0.43
     slipper
    0.42
     propagand
    0.42
     briefing
    0.42
    ero
    0.41
    Activations Density 0.001%

    No Known Activations