© 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. 123718
    Prev
    Next
    INDEX
    Explanations

    NASCAR racing

    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
     üblichen
    -1.38
     çalışma
    -1.35
     legais
    -1.35
     reinen
    -1.32
     größeren
    -1.24
     solchen
    -1.21
     recentes
    -1.20
     gemeinsamen
    -1.20
    paravant
    -1.18
     animados
    -1.17
    POSITIVE LOGITS
    裢
    1.55
    ༵
    1.46
    ႐
    1.30
    ᡴ
    1.24
     spesielt
    1.23
    咽
    1.23
     hain
    1.23
    azioni
    1.21
    ATION
    1.18
    
    1.16
    Activations Density 0.017%

    No Known Activations