© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1209
    Prev
    Next
    INDEX
    Explanations

    usar, usando, usada, use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    珰
    -2.59
    朥
    -2.55
    饪
    -2.52
    鍆
    -2.45
     花纹
    -2.44
    圌
    -2.33
    ți
    -2.31
    鉏
    -2.31
    驁
    -2.30
    雳
    -2.27
    POSITIVE LOGITS
    ↵↵
    3.88
    𖣘
    2.75
    ak
    2.19
    $
    2.09
    ff
    1.99
     in
    1.99
     impec
    1.99
     внима
    1.91
    みたら
    1.91
     problemów
    1.91
    Activations Density 0.002%

    No Known Activations