© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43664
    Prev
    Next
    INDEX
    Explanations

    sports outcomes and statistics

    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
     móveis
    -1.57
     brinquedos
    -1.44
     its
    -1.40
    歺
    -1.38
    
    -1.37
     now
    -1.34
    咈
    -1.33
    憷
    -1.32
    
    -1.30
     adesivos
    -1.28
    POSITIVE LOGITS
    ୈ
    1.34
     verkar
    1.19
    ))).
    1.18
     Krankenhaus
    1.16
     utama
    1.13
    =
    1.11
    Neem
    1.10
     on
    1.08
     fortsätter
    1.08
     assist
    1.07
    Activations Density 0.709%

    No Known Activations