© 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. 70891
    Prev
    Next
    INDEX
    Explanations

    physics equations and concepts

    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
     السياس
    -1.19
     time
    -1.15
     stadt
    -1.09
     getAddress
    -1.09
     method
    -1.08
     process
    -1.06
     What
    -1.04
     manager
    -1.00
     attempt
    -0.99
     memberId
    -0.99
    POSITIVE LOGITS
     vider
    1.20
     vaksin
    1.19
     jugu
    1.18
     menyenangkan
    1.16
    Titel
    1.16
    !」
    1.14
    Enfant
    1.12
    Predicted
    1.12
    Sozial
    1.10
     cerah
    1.09
    Activations Density 0.017%

    No Known Activations