© 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. 1372
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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
    herstellung
    -1.33
     noodzake
    -1.29
     inova
    -1.27
     mainten
    -1.27
     vicente
    -1.25
     giudice
    -1.21
     fernández
    -1.21
     onderhoud
    -1.21
     severa
    -1.20
     seperti
    -1.20
    POSITIVE LOGITS
     may
    1.45
     we
    1.41
     this
    1.30
     you
    1.29
    ícias
    1.28
     their
    1.26
     kuhusu
    1.25
     инстру
    1.24
     that
    1.23
     new
    1.20
    Activations Density 0.246%

    No Known Activations