© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79545
    Prev
    Next
    INDEX
    Explanations

    questions starting with did

    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_22/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
    要不然
    -2.59
     zwanzig
    -2.33
    柺
    -2.28
     sieben
    -2.23
    ↵
    -2.16
     logistical
    -2.13
    ments
    -2.11
    ጧ
    -2.11
     zahlreichen
    -2.08
    síða
    -2.06
    POSITIVE LOGITS
    ’
    3.59
    鯪
    2.41
     LEONARD
    2.11
     russo
    2.08
     kilomètres
    2.06
     était
    2.05
     sains
    2.00
    🌷
    1.99
    ,
    1.98
     Архиви
    1.97
    Activations Density 0.018%

    No Known Activations