© 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. 110790
    Prev
    Next
    INDEX
    Explanations

    Caribbean countries and peoples

    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
    不夠
    -1.14
     också
    -1.13
    spunk
    -1.09
     綿
    -1.09
     formatted
    -1.09
     perſ
    -1.07
     Muerte
    -1.05
     قبول
    -1.05
     klikken
    -1.02
     camioneta
    -1.02
    POSITIVE LOGITS
     long
    1.35
    ifiquement
    1.17
     may
    1.13
    USTAIN
    1.10
    ↵
    1.06
    IActionResult
    1.05
    руется
    1.03
     it
    1.02
     other
    1.02
     wurde
    1.01
    Activations Density 0.062%

    No Known Activations