© 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. 10148
    Prev
    Next
    INDEX
    Explanations

    describing periods of 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
     it
    -1.60
     is
    -1.59
     ПОД
    -1.55
    if
    -1.54
     پارس
    -1.53
    any
    -1.53
    [
    -1.53
     چیه
    -1.45
    new
    -1.44
    﨑
    -1.44
    POSITIVE LOGITS
    CHREIBUNG
    1.66
     year
    1.56
     days
    1.54
     contratación
    1.54
     but
    1.43
    でしたが
    1.42
     participó
    1.40
    がありますが
    1.38
     guerres
    1.38
     ferrovia
    1.34
    Activations Density 0.074%

    No Known Activations