© 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. 102454
    Prev
    Next
    INDEX
    Explanations

    circuit court dates

    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
     которы
    -1.54
     jste
    -1.50
     flesta
    -1.44
    alties
    -1.41
     correctes
    -1.39
     triom
    -1.38
     enthou
    -1.37
    ApplicationTests
    -1.35
     nocy
    -1.34
    bringt
    -1.30
    POSITIVE LOGITS
     it
    2.53
     only
    1.55
    ↵↵
    1.53
    .”
    1.50
     what
    1.48
    </em>
    1.45
     not
    1.42
    nové
    1.38
    it
    1.38
     same
    1.33
    Activations Density 1.230%

    No Known Activations