© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129484
    Prev
    Next
    INDEX
    Explanations

    non-english words and symbols

    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
    3
    -2.52
    梣
    -2.31
    2
    -2.31
    1
    -2.25
    ቼ
    -2.13
    是什么意思
    -2.11
    .---
    -2.05
    她
    -2.05
     キャンペーン
    -2.03
    4
    -2.03
    POSITIVE LOGITS
     
    2.77
    眨眼
    1.98
    ↵↵
    1.98
     testigos
    1.91
     einigen
    1.89
     nincs
    1.86
    汩
    1.84
     Süden
    1.81
     —
    1.80
    ぶつ
    1.78
    Activations Density 0.010%

    No Known Activations