© 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. 12420
    Prev
    Next
    INDEX
    Explanations

    US contexts

    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
     bedeutet
    -1.59
     потім
    -1.55
    苼
    -1.49
     partout
    -1.45
    bluza
    -1.42
    mathrm
    -1.41
     komfort
    -1.37
    ="
    -1.34
     сначала
    -1.33
    皛
    -1.33
    POSITIVE LOGITS
    US
    1.45
     teilweise
    1.44
     несмотря
    1.38
     US
    1.37
    er
    1.37
    々な
    1.32
    范围内
    1.32
    🇺🇸
    1.29
     citizens
    1.27
    是怎么
    1.25
    Activations Density 0.135%

    No Known Activations