© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3591
    Prev
    Next
    INDEX
    Explanations

    forenames in academic texts

    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
     สำหรับ
    -1.49
    引言
    -1.38
     Foire
    -1.33
    焌
    -1.32
    Médaille
    -1.32
    Tiene
    -1.30
     innego
    -1.28
    柠
    -1.27
     vermelhas
    -1.27
    气息
    -1.27
    POSITIVE LOGITS
     are
    1.50
    )
    1.40
     $-$
    1.35
    OS
    1.31
     elbise
    1.28
    董事
    1.23
     Sometime
    1.23
    (
    1.21
     protože
    1.21
     who
    1.21
    Activations Density 0.099%

    No Known Activations