© 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. 60995
    Prev
    Next
    INDEX
    Explanations

    in German or English locations

    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
    k
    -3.08
    {
    -3.00
     selben
    -2.69
    ur
    -2.61
     Hinblick
    -2.58
    ",
    -2.45
     estekak
    -2.42
    *
    -2.42
    man
    -2.41
    te
    -2.33
    POSITIVE LOGITS
    蹀
    2.50
    ௅
    2.48
    笵
    2.36
    拶
    2.28
     केवल
    2.19
     drugi
    2.19
     reaping
    2.17
    ⃙
    2.17
    趼
    2.16
    我能
    2.11
    Activations Density 0.002%

    No Known Activations