© 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. 103094
    Prev
    Next
    INDEX
    Explanations

    upside down or inverted

    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
     But
    -2.20
    S
    -2.06
    ING
    -1.95
    EN
    -1.94
     to
    -1.88
     namun
    -1.82
     folgende
    -1.77
    大丈夫です
    -1.69
    O
    -1.67
    ter
    -1.66
    POSITIVE LOGITS
     environ
    1.81
    ayaquil
    1.73
     bordado
    1.63
     idyl
    1.62
     یا
    1.62
    
    1.61
     giyim
    1.60
     plastik
    1.59
     supermercado
    1.59
    鯓
    1.56
    Activations Density 0.014%

    No Known Activations