© 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. 945
    Prev
    Next
    INDEX
    Explanations

    words starting with res

    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
    犼
    -2.83
    and
    -2.53
    驁
    -2.27
     facendo
    -2.20
     și
    -2.20
     и
    -2.20
    长时间
    -2.14
    悽
    -2.09
    CHREIB
    -2.08
     και
    -2.03
    POSITIVE LOGITS
    Подготовка
    2.27
    ة
    2.22
    {
    2.20
     \
    2.19
    在我
    2.11
     odeur
    2.06
    鯢
    2.06
    ing
    2.06
    –
    2.05
    
    2.05
    Activations Density 0.003%

    No Known Activations