© 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. 43545
    Prev
    Next
    INDEX
    Explanations

    sequential progression

    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
     både
    -1.30
     toit
    -1.29
    зья
    -1.26
     fraiche
    -1.20
     soms
    -1.19
    iree
    -1.17
     germain
    -1.16
     и
    -1.14
     Wikipédia
    -1.13
     anty
    -1.13
    POSITIVE LOGITS
     then
    1.75
     now
    1.46
     concerning
    1.45
    搜尋
    1.32
     civilización
    1.27
     não
    1.18
     though
    1.16
    couvrez
    1.16
    と思ったら
    1.15
     gewiß
    1.13
    Activations Density 0.172%

    No Known Activations