© 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. 227
    Prev
    Next
    INDEX
    Explanations

    morphed, day, traction

    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
     zahlreichen
    -1.52
     einzigartigen
    -1.52
    </h5>
    -1.46
     sicheren
    -1.45
    年来
    -1.41
     Konkurrenz
    -1.39
     direkten
    -1.38
    "));
    -1.37
     unmittel
    -1.36
     Hinblick
    -1.35
    POSITIVE LOGITS
    (￣
    1.32
    　(
    1.30
     dve
    1.28
     incluse
    1.25
     leves
    1.25
     materi
    1.25
    bof
    1.22
    bten
    1.20
     samh
    1.20
     efic
    1.16
    Activations Density 0.553%

    No Known Activations