© 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. 12058
    Prev
    Next
    INDEX
    Explanations

    giving attention or priority

    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
     a
    -1.48
    “
    -1.45
     other
    -1.44
    "<
    -1.38
     from
    -1.35
     With
    -1.34
     provide
    -1.33
    (
    -1.24
    тт
    -1.24
     große
    -1.22
    POSITIVE LOGITS
     masz
    1.74
    蟥
    1.72
     attention
    1.66
    genodigd
    1.63
    鹋
    1.59
    纡
    1.59
    attention
    1.58
     mojej
    1.54
     betekent
    1.51
    seitigen
    1.49
    Activations Density 0.031%

    No Known Activations