© 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. 10-GEMMASCOPE-RES-131K
    4. 80782
    Prev
    Next
    INDEX
    Explanations

    with quantity or time

    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
     où
    -1.70
    lemented
    -1.66
    我们的
    -1.61
     länder
    -1.56
    igte
    -1.55
     Köz
    -1.52
    ﮭ
    -1.52
    我的
    -1.48
    магазин
    -1.48
    ynchronous
    -1.47
    POSITIVE LOGITS
     they
    2.16
     then
    1.76
    and
    1.66
     after
    1.59
    }$
    1.59
     end
    1.58
     applies
    1.55
     deciding
    1.55
     than
    1.52
     there
    1.46
    Activations Density 0.015%

    No Known Activations