© 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. 130909
    Prev
    Next
    INDEX
    Explanations

    diacritics and special characters

    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
    渽
    -3.34
    jdons
    -2.94
    Certainly
    -2.64
    ڧ
    -2.52
    ashqai
    -2.52
     möjlighet
    -2.42
    حياته
    -2.41
     แต่
    -2.38
    Probably
    -2.34
     ถ้า
    -2.34
    POSITIVE LOGITS
    呖
    3.13
    s
    3.00
    you
    2.98
    媪
    2.97
     we
    2.83
    鰱
    2.72
    骉
    2.70
    на
    2.67
    es
    2.64
    al
    2.58
    Activations Density 0.001%

    No Known Activations