© 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. 105849
    Prev
    Next
    INDEX
    Explanations

    Canadian entities and contexts

    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
    \
    -3.30
     เพราะ
    -3.13
     или
    -2.94
     atau
    -2.72
     The
    -2.45
     '
    -2.36
     impec
    -2.34
     {
    -2.34
    不宜
    -2.33
     ailing
    -2.31
    POSITIVE LOGITS
     yf
    2.66
    咈
    2.63
    ization
    2.55
    猡
    2.50
    </h1>
    2.48
    缫
    2.48
     liet
    2.45
     isra
    2.42
     poil
    2.41
    阄
    2.41
    Activations Density 0.010%

    No Known Activations