© 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. 34-GEMMASCOPE-RES-131K
    7. 38367
    Prev
    Next
    INDEX
    Explanations

    grade and listed status

    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_34/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
     formalized
    -0.78
     kanya
    -0.77
    现在的
    -0.77
    鄱
    -0.77
    versiti
    -0.77
     ateliers
    -0.75
    𝒉
    -0.74
    そうな
    -0.74
     验证
    -0.73
    hrte
    -0.72
    POSITIVE LOGITS
     Grade
    2.61
     Listed
    2.31
     listed
    2.20
     grade
    2.02
    Grade
    1.95
    Listed
    1.94
    listed
    1.86
     GRADE
    1.75
     listing
    1.59
     Listing
    1.58
    Activations Density 0.043%

    No Known Activations