© 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. 43620
    Prev
    Next
    INDEX
    Explanations

    phone numbers and codes

    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
    .
    -2.81
    ’
    -2.36
    ↵↵
    -2.22
    但我
    -2.09
     provavelmente
    -2.02
     is
    -1.97
     gostar
    -1.96
    所以我
    -1.95
     houve
    -1.88
     
    -1.88
    POSITIVE LOGITS
     ſte
    3.00
    凩
    2.78
    ⢅
    2.47
    ⬮
    2.41
    
    2.34
    褡
    2.28
    鮰
    2.27
    蜮
    2.27
    基本的
    2.20
    噥
    2.19
    Activations Density 0.016%

    No Known Activations