© 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. 13625
    Prev
    Next
    INDEX
    Explanations

    listen to

    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
    觔
    -2.72
    ሷ
    -2.61
     belangrij
    -2.55
     tačiau
    -2.55
     waarschijnlijk
    -2.47
     for
    -2.45
    寳
    -2.45
    霙
    -2.44
     zweiten
    -2.41
    闿
    -2.41
    POSITIVE LOGITS
    -
    4.31
    {
    2.92
    \
    2.91
    她
    2.84
    1
    2.67
    Kelebihan
    2.63
    是
    2.44
     wunderbar
    2.38
    的就
    2.38
    的他
    2.36
    Activations Density 0.003%

    No Known Activations