© 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. 74656
    Prev
    Next
    INDEX
    Explanations

    XML element names

    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
     to
    -1.55
     conscienti
    -1.41
     bequeathed
    -1.41
     ursprünglichen
    -1.35
    愎
    -1.34
     horrend
    -1.34
     obses
    -1.30
     their
    -1.28
     hierbei
    -1.27
     Ваш
    -1.26
    POSITIVE LOGITS
    {
    1.82
    ïdes
    1.62
    rrrrrrrr
    1.59
    ꗃ
    1.59
     каж
    1.59
     harapan
    1.54
    jublj
    1.48
     distinct
    1.45
     projets
    1.43
    瑧
    1.41
    Activations Density 0.056%

    No Known Activations