© 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. 22-GEMMASCOPE-RES-131K
    7. 70366
    Prev
    Next
    INDEX
    Explanations

    time and temperature records

    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
    靱
    -1.31
    Elő
    -1.24
     Geistes
    -1.23
     your
    -1.23
     conocer
    -1.20
    approximately
    -1.16
     diseñador
    -1.13
    )=>{
    -1.11
     orice
    -1.11
    about
    -1.11
    POSITIVE LOGITS
     Tuesday
    1.65
    อร่อย
    1.61
     yesterday
    1.61
     Thursday
    1.50
    edificio
    1.46
     Wednesday
    1.45
     February
    1.44
     Monday
    1.43
     this
    1.43
     Saturday
    1.41
    Activations Density 0.026%

    No Known Activations